© 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. 5151
    Prev
    Next
    INDEX
    Explanations

    interrogative words related to identity and location

    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
    57
    +0.12
    0.5%
    186
    +0.12
    0.5%
    430
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.12
    0.04
    662
    +0.12
    0.04
    57
    +0.11
    0.03
    Negative Logits
    artifacts
    -0.67
    astern
    -0.64
    Interstitial
    -0.63
     amy
    -0.57
    waves
    -0.56
     WATCHED
    -0.55
    é¾įåĸļ士
    -0.55
     suscept
    -0.54
     validity
    -0.53
     resid
    -0.53
    POSITIVE LOGITS
    uer
    0.73
     they
    0.67
    lled
    0.66
    itiveness
    0.65
     THEY
    0.64
    hest
    0.63
     you
    0.63
    they
    0.60
     thou
    0.60
    usual
    0.59
    Activations Density 0.260%

    No Known Activations