© 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. 5503
    Prev
    Next
    INDEX
    Explanations

    dimensions and specifications for images or graphics

    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
    35
    +0.10
    0.5%
    477
    +0.10
    0.5%
    589
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.10
    0.02
    394
    +0.10
    0.02
    501
    +0.10
    0.02
    Negative Logits
    £ı
    -0.75
     ausp
    -0.69
    romy
    -0.63
     Everyday
    -0.61
    ©¶æ
    -0.61
    Ö¼
    -0.59
     Mend
    -0.56
     domest
    -0.55
     Kuala
    -0.55
     associations
    -0.55
    POSITIVE LOGITS
    pixel
    0.90
    interstitial
    0.80
    height
    0.76
    "}
    0.72
    border
    0.71
     pixels
    0.70
    "]
    0.69
    align
    0.68
    "></
    0.68
     tallest
    0.68
    Activations Density 0.128%

    No Known Activations