© 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. 4136
    Prev
    Next
    INDEX
    Explanations

    references to economic distress and administrative responses

    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
    537
    +0.10
    0.5%
    528
    +0.10
    0.5%
    313
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.10
    0.24
    640
    +0.10
    0.19
    145
    +0.10
    0.15
    Negative Logits
    ä
    -0.76
    ographically
    -0.75
    him
    -0.74
    antically
    -0.73
    borne
    -0.70
    lyak
    -0.69
    iton
    -0.68
    emort
    -0.68
    ifest
    -0.67
    desc
    -0.67
    POSITIVE LOGITS
     Lastly
    0.75
    anguage
    0.75
     Roads
    0.73
     Meanwhile
    0.73
    reements
    0.72
     Violence
    0.64
    Veh
    0.64
     Taxes
    0.63
    }}}
    0.62
     Airl
    0.61
    Activations Density 1.727%

    No Known Activations