© 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. 4994
    Prev
    Next
    INDEX
    Explanations

    various terms related to programming and computer commands

    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
    167
    +0.10
    0.5%
    551
    +0.10
    0.4%
    121
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.10
    0.01
    477
    +0.10
    0.00
    284
    +0.09
    0.01
    Negative Logits
     intrig
    -0.71
    geries
    -0.71
     distracting
    -0.71
     offending
    -0.62
    clair
    -0.59
     explan
    -0.59
     gratification
    -0.58
    nces
    -0.58
     answ
    -0.58
     tc
    -0.58
    POSITIVE LOGITS
    и
    0.92
    æѦ
    0.90
    é¾įå
    0.89
    ij
    0.83
    à¸
    0.82
    æ©Ł
    0.81
    ITAL
    0.79
     æľ
    0.79
    姫
    0.78
    ãĥīãĥ©
    0.76
    Activations Density 0.014%

    No Known Activations