Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5045
    Prev
    Next
    INDEX
    Explanations

    dates and references to mortality

    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
    627
    +0.10
    0.5%
    321
    +0.10
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    627
    +0.10
    0.03
    6
    +0.10
    0.07
    127
    +0.09
    0.04
    Negative Logits
    Reviewer
    -0.81
     barriers
    -0.63
    igent
    -0.60
    perse
    -0.60
     guiIcon
    -0.59
     diction
    -0.59
    ealous
    -0.59
     whisk
    -0.58
     breathing
    -0.57
     stret
    -0.57
    POSITIVE LOGITS
     2009
    1.46
     2005
    1.45
     2006
    1.45
     October
    1.45
     1999
    1.45
     January
    1.44
     September
    1.43
     February
    1.43
     1979
    1.41
     April
    1.41
    Activations Density 1.068%

    No Known Activations