© 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. 6218
    Prev
    Next
    INDEX
    Explanations

    suffixes that indicate relationships, conditions, or attributes

    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
    674
    +0.11
    0.5%
    708
    +0.10
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    0.01
    503
    +0.10
    0.03
    555
    +0.10
    0.03
    Negative Logits
     1886
    -0.75
    USER
    -0.69
    ACTED
    -0.63
    è£ħ
    -0.60
     1899
    -0.60
     1905
    -0.59
    orses
    -0.59
    users
    -0.59
    iewicz
    -0.58
    yne
    -0.58
    POSITIVE LOGITS
    rification
    0.91
    rit
    0.90
    ROR
    0.88
    rors
    0.86
    rible
    0.86
    rified
    0.82
    rants
    0.82
    vous
    0.82
    bert
    0.78
    rill
    0.78
    Activations Density 0.282%

    No Known Activations