© 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 EvalsExportsinterp-engineNEWAPI 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. 5158
    Prev
    Next
    INDEX
    Explanations

    terms related to data structure operations, specifically those involving push and pull actions

    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
    314
    +0.13
    0.6%
    649
    +0.12
    0.5%
    739
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    140
    +0.13
    0.02
    50
    +0.12
    0.02
    28
    +0.09
    0.02
    Negative Logits
     Masquerade
    -0.78
     boundaries
    -0.68
     affordability
    -0.64
     Geral
    -0.61
     Nieto
    -0.61
     onward
    -0.61
    izons
    -0.59
     Leap
    -0.59
     relentlessly
    -0.59
    uate
    -0.59
    POSITIVE LOGITS
    letter
    1.05
    airs
    0.88
    ris
    0.86
    turn
    0.83
    ops
    0.81
    oly
    0.80
    letters
    0.79
    mail
    0.79
    alter
    0.79
    erton
    0.78
    Activations Density 0.071%

    No Known Activations