Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5035
    Prev
    Next
    INDEX
    Explanations

    significant numerical values or indicators related to contracts and agreements

    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
    490
    +0.11
    0.5%
    521
    +0.10
    0.5%
    44
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.11
    0.00
    521
    +0.10
    0.00
    568
    +0.09
    0.01
    Negative Logits
    minecraft
    -0.80
    fr
    -0.74
     Franks
    -0.68
    cre
    -0.66
     hoard
    -0.66
    ozo
    -0.65
    yip
    -0.65
    nikov
    -0.65
    gress
    -0.65
    arth
    -0.64
    POSITIVE LOGITS
     Shinji
    1.13
     Asuka
    0.96
    Eva
    0.88
     Unit
    0.86
     Rei
    0.84
    ãĤ®
    0.82
     Eva
    0.80
     Athena
    0.75
     Actress
    0.74
     Devi
    0.73
    Activations Density 0.037%

    No Known Activations