© 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. 10-RES_POST_32K-OAI
    11. 28667
    Prev
    Next
    INDEX
    Explanations

    terms related to zombies and the undead

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    258
    +0.10
    0.5%
    154
    +0.10
    0.4%
    445
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.03
    719
    +0.10
    0.02
    556
    +0.10
    0.01
    Negative Logits
    wegian
    -0.78
    odore
    -0.76
    cases
    -0.76
    agall
    -0.76
    ional
    -0.75
    fman
    -0.74
    tons
    -0.74
    stro
    -0.73
    ajo
    -0.72
    ogyn
    -0.72
    POSITIVE LOGITS
     apocalypse
    1.23
     Apocalypse
    1.03
     horde
    1.03
     outbreak
    0.92
     hordes
    0.90
    ombies
    0.88
     scourge
    0.78
    Rush
    0.78
     Chow
    0.77
     plague
    0.76
    Activations Density 0.115%

    No Known Activations