© 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. 4436
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of imperfection or flaws

    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
    308
    +0.10
    0.4%
    232
    +0.10
    0.4%
    59
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.10
    0.01
    13
    +0.10
    0.01
    232
    +0.09
    0.01
    Negative Logits
    anwhile
    -0.68
     GOODMAN
    -0.65
     Carbuncle
    -0.64
     Chrys
    -0.64
     Aval
    -0.60
     Hath
    -0.60
     Ou
    -0.60
    wagen
    -0.59
    MpServer
    -0.58
     revolving
    -0.58
    POSITIVE LOGITS
    vious
    1.33
    manent
    1.31
    ishable
    1.16
    missible
    1.11
    cept
    0.96
    idium
    0.93
    miss
    0.93
    missive
    0.93
    bably
    0.90
    ceivable
    0.89
    Activations Density 0.018%

    No Known Activations