© 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. 4919
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate minimal quantity or impact

    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
    455
    +0.11
    0.5%
    376
    +0.10
    0.5%
    444
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.11
    0.04
    455
    +0.10
    0.04
    344
    +0.10
    0.03
    Negative Logits
    agents
    -0.74
    dor
    -0.68
    hov
    -0.67
    ulin
    -0.65
    ousand
    -0.65
    ams
    -0.64
    ammad
    -0.63
    otton
    -0.62
    ocard
    -0.62
    hani
    -0.60
    POSITIVE LOGITS
     else
    1.02
     whatsoever
    0.91
     indication
    0.91
     doubt
    0.86
     resemblance
    0.82
     except
    0.80
     semblance
    0.78
     recourse
    0.77
     consolation
    0.76
     explanation
    0.76
    Activations Density 0.071%

    No Known Activations