© 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 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. 5060
    Prev
    Next
    INDEX
    Explanations

    references to specific days

    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
    515
    +0.10
    0.4%
    651
    +0.09
    0.4%
    318
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.10
    0.06
    383
    +0.09
    0.04
    240
    +0.09
    0.04
    Negative Logits
    ategory
    -0.77
     externalToEVAOnly
    -0.75
    emort
    -0.75
    emale
    -0.70
    ngth
    -0.69
    amily
    -0.68
    umbn
    -0.67
     Osw
    -0.67
    essee
    -0.65
    ancies
    -0.65
    POSITIVE LOGITS
    dream
    1.60
    care
    1.25
    break
    1.03
    light
    0.97
    lights
    0.94
    motion
    0.88
    long
    0.88
    flower
    0.84
    nings
    0.81
    life
    0.80
    Activations Density 0.178%

    No Known Activations