© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 8672
    Prev
    Next
    INDEX
    Explanations

    references to photos and visual content, particularly in the context of storytelling and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    27
    +0.11
    0.5%
    767
    +0.10
    0.5%
    479
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.11
    0.04
    97
    +0.10
    0.03
    6
    +0.10
    0.05
    Negative Logits
     urgency
    -0.75
     persuasion
    -0.74
     expectation
    -0.73
     itch
    -0.68
     moderation
    -0.68
     assumption
    -0.66
     invitation
    -0.66
    alties
    -0.65
     sincerity
    -0.65
     temptation
    -0.64
    POSITIVE LOGITS
    PHOTOS
    1.00
    OTOS
    0.99
    Photos
    0.98
    WATCH
    0.91
     Scenes
    0.91
     Photos
    0.91
    Featured
    0.87
     Photographer
    0.84
    htaking
    0.82
     VIDEOS
    0.81
    Activations Density 0.461%

    No Known Activations