© 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. 5475
    Prev
    Next
    INDEX
    Explanations

    conversational exchanges and interjections in dialogue

    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
    246
    +0.13
    0.6%
    373
    +0.12
    0.5%
    392
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    544
    +0.13
    0.05
    267
    +0.12
    0.06
    572
    +0.10
    0.06
    Negative Logits
    Thus
    -0.88
    avez
    -0.82
    Therefore
    -0.80
     hitherto
    -0.77
     Inquiry
    -0.71
    ãĤº
    -0.70
    Enter
    -0.68
    ĵĺ
    -0.68
     unlawfully
    -0.67
     desired
    -0.67
    POSITIVE LOGITS
     yeah
    1.22
    yeah
    1.19
     dude
    1.12
    Yeah
    1.12
     dunno
    1.10
     gotta
    1.06
     ya
    1.04
     Yeah
    1.02
     fuckin
    1.02
     dudes
    1.02
    Activations Density 0.401%

    No Known Activations