© 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. 8097
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases or compound words

    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
    36
    +0.21
    1.0%
    373
    +0.13
    0.6%
    250
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.21
    0.02
    639
    +0.13
    0.02
    102
    +0.12
    0.02
    Negative Logits
    APD
    -0.76
    çĶ°
    -0.72
    PsyNetMessage
    -0.72
    UTF
    -0.68
     Armed
    -0.66
     Ard
    -0.65
     Administ
    -0.64
     Orche
    -0.64
    inen
    -0.64
     Arctic
    -0.62
    POSITIVE LOGITS
    ccording
    1.08
    dozen
    0.93
    cl
    0.83
    mob
    0.83
    rency
    0.82
    holes
    0.81
    lot
    0.81
    cling
    0.81
    half
    0.80
    minute
    0.80
    Activations Density 0.075%

    No Known Activations