© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6696
    Prev
    Next
    INDEX
    Explanations

    phrases that express probabilities or chances of outcomes

    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
    373
    +0.12
    0.6%
    430
    +0.11
    0.5%
    661
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.12
    0.02
    78
    +0.11
    0.01
    244
    +0.10
    0.02
    Negative Logits
     horm
    -0.76
     metaphors
    -0.67
     lifes
    -0.64
     metaphor
    -0.64
     detrim
    -0.63
     shortcuts
    -0.62
     collapses
    -0.61
     possibilities
    -0.60
    raph
    -0.59
     inexper
    -0.59
    POSITIVE LOGITS
    Ele
    0.71
    renheit
    0.70
    Prev
    0.68
    Rot
    0.64
    ison
    0.63
    omin
    0.63
    percent
    0.63
    per
    0.62
    onica
    0.62
    ardi
    0.61
    Activations Density 0.087%

    No Known Activations