© 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. 8412
    Prev
    Next
    INDEX
    Explanations

    terms related to 'urs' and suggest a focus on the concept of 'cursory reviews' or 'overview evaluations.'

    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
    373
    +0.14
    0.7%
    195
    +0.11
    0.5%
    151
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.14
    0.01
    284
    +0.11
    0.01
    151
    +0.10
    0.01
    Negative Logits
     Bayer
    -0.69
     Ambro
    -0.65
     Breaker
    -0.63
     Swed
    -0.62
     Manip
    -0.61
    agna
    -0.60
    heit
    -0.59
    aan
    -0.58
     Tunis
    -0.58
     Butcher
    -0.58
    POSITIVE LOGITS
    uits
    1.11
    uit
    1.09
    hip
    1.07
    ibilities
    0.94
    itized
    0.89
    geons
    0.89
    atile
    0.86
    uous
    0.85
    ury
    0.85
    uries
    0.85
    Activations Density 0.049%

    No Known Activations