© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4992
    Prev
    Next
    INDEX
    Explanations

    reference to significant political concepts and movements

    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
    756
    +0.20
    0.9%
    160
    +0.09
    0.4%
    365
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.20
    0.20
    608
    +0.09
    0.17
    393
    +0.09
    0.13
    Negative Logits
    Alert
    -0.91
    poke
    -0.86
    ocket
    -0.84
     GoPro
    -0.78
     Emails
    -0.77
     vet
    -0.75
    Todd
    -0.74
     Amount
    -0.71
    6666
    -0.70
     Yards
    -0.70
    POSITIVE LOGITS
     subord
    1.25
     imperialist
    1.23
     neoliberal
    1.22
     capitalist
    1.20
     bourgeois
    1.19
     proletarian
    1.17
     ideological
    1.15
     Marxist
    1.13
     emanc
    1.12
     societies
    1.11
    Activations Density 0.915%

    No Known Activations