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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4569
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with statistics or metrics

    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
    357
    +0.08
    0.4%
    127
    +0.08
    0.3%
    440
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.08
    0.03
    95
    +0.08
    0.03
    230
    +0.07
    0.03
    Negative Logits
    ittees
    -0.83
    ocrats
    -0.71
    ships
    -0.69
    shop
    -0.68
    ielding
    -0.67
    ctor
    -0.67
    meet
    -0.67
     desks
    -0.65
    alties
    -0.64
     Rite
    -0.64
    POSITIVE LOGITS
     sensitivity
    0.94
     acceleration
    0.81
     pressure
    0.78
     precision
    0.78
     damage
    0.77
     warmth
    0.77
     susceptibility
    0.74
     accuracy
    0.74
    ITNESS
    0.74
     insight
    0.73
    Activations Density 0.201%

    No Known Activations