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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 4445
    Prev
    Next
    INDEX
    Explanations

    patterns related to regular expressions and string handling

    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
    494
    +0.12
    0.5%
    57
    +0.11
    0.5%
    526
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    364
    +0.12
    0.06
    503
    +0.11
    0.04
    326
    +0.10
    0.05
    Negative Logits
    Reviewer
    -0.65
     contag
    -0.63
     lif
    -0.61
     readiness
    -0.60
     delegation
    -0.58
     Semin
    -0.58
     attendance
    -0.58
     maturity
    -0.57
     facilit
    -0.57
     behaviors
    -0.56
    POSITIVE LOGITS
    \\
    1.16
    \/
    1.04
    \\\\
    1.02
    \-
    0.96
    ]+
    0.96
    \.
    0.92
    (\
    0.88
     \\
    0.88
    Ïī
    0.87
    /,
    0.85
    Activations Density 0.393%

    No Known Activations