© 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. 4212
    Prev
    Next
    INDEX
    Explanations

    references to precision and thoroughness in descriptions

    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
    7
    +0.13
    0.6%
    255
    +0.12
    0.6%
    302
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.13
    0.02
    724
    +0.12
    0.02
    195
    +0.10
    0.01
    Negative Logits
    onz
    -0.80
    orea
    -0.78
    ofi
    -0.74
    loo
    -0.72
    esta
    -0.71
    byn
    -0.69
    berman
    -0.66
    encrypted
    -0.66
    ccoli
    -0.65
    choes
    -0.64
    POSITIVE LOGITS
    ured
    0.97
    uring
    0.81
     detail
    0.78
    iencies
    0.78
    urers
    0.77
    ures
    0.74
    smanship
    0.74
    worker
    0.73
    itiveness
    0.73
    work
    0.72
    Activations Density 0.106%

    No Known Activations