© 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. 5006
    Prev
    Next
    INDEX
    Explanations

    references to personal narratives or subjective experiences

    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
    125
    +0.11
    0.5%
    397
    +0.10
    0.5%
    445
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.05
    608
    +0.10
    0.04
    616
    +0.10
    0.04
    Negative Logits
    ļéĨĴ
    -0.78
    phabet
    -0.67
    izons
    -0.61
    illion
    -0.59
    ħĭ
    -0.57
     existed
    -0.56
    cel
    -0.56
    phony
    -0.56
    ry
    -0.56
    ¥µ
    -0.55
    POSITIVE LOGITS
     duty
    1.08
     responsibility
    0.88
     intention
    0.86
     safest
    0.86
    duty
    0.78
     easiest
    0.76
     raining
    0.76
     respons
    0.73
    erest
    0.73
     nature
    0.72
    Activations Density 0.211%

    No Known Activations