© 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. 8-RES_POST_32K-OAI
    11. 6786
    Prev
    Next
    INDEX
    Explanations

    instances of conflict and negotiation in social situations

    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
    745
    +0.11
    0.5%
    762
    +0.09
    0.4%
    36
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.11
    0.11
    271
    +0.09
    0.06
    750
    +0.09
    0.05
    Negative Logits
    ividual
    -0.71
    liam
    -0.69
    ousands
    -0.69
    oreal
    -0.68
    itudinal
    -0.67
     globally
    -0.65
    uably
    -0.64
     disproportionately
    -0.64
     Cabin
    -0.63
     internationally
    -0.63
    POSITIVE LOGITS
     politely
    0.88
     relent
    0.85
     hurried
    0.83
     reluctantly
    0.81
     pleas
    0.80
     precaution
    0.80
     momentarily
    0.77
     calmed
    0.77
     hesitation
    0.77
     adjourn
    0.75
    Activations Density 1.919%

    No Known Activations