© 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. 5484
    Prev
    Next
    INDEX
    Explanations

    terms related to political strategy and maneuvering

    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
    288
    +0.12
    0.6%
    23
    +0.12
    0.5%
    271
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.03
    326
    +0.12
    0.02
    271
    +0.12
    0.02
    Negative Logits
    ened
    -0.67
    inite
    -0.65
    algia
    -0.64
     Garfield
    -0.64
    ony
    -0.63
     Anon
    -0.63
    iciency
    -0.62
    ħĭ
    -0.61
    Interstitial
    -0.61
    seys
    -0.61
    POSITIVE LOGITS
    ments
    1.06
     maneuvers
    1.01
     maneuver
    0.97
    nel
    0.89
    ability
    0.87
    tainment
    0.85
    eering
    0.83
    ably
    0.79
    abulary
    0.79
    ATIONS
    0.79
    Activations Density 0.102%

    No Known Activations