© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 6065
    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 @ 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
    99
    +0.11
    0.5%
    566
    +0.11
    0.5%
    258
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.02
    99
    +0.11
    0.02
    326
    +0.10
    0.02
    Negative Logits
    ional
    -0.83
    metics
    -0.74
    İ
    -0.74
    wegian
    -0.73
    ours
    -0.73
    odore
    -0.71
    Oracle
    -0.70
    %]
    -0.70
    å§«
    -0.70
    vor
    -0.70
    POSITIVE LOGITS
     apocalypse
    1.14
     horde
    1.00
     hordes
    0.90
     Apocalypse
    0.85
    ombies
    0.80
     Chow
    0.77
     outbreak
    0.77
     virus
    0.72
     scourge
    0.72
     Horde
    0.67
    Activations Density 0.084%

    No Known Activations