© 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. 8450
    Prev
    Next
    INDEX
    Explanations

    words related to medical and therapeutic contexts

    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
    22
    +0.10
    0.5%
    703
    +0.09
    0.4%
    641
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.10
    0.01
    394
    +0.09
    0.01
    247
    +0.09
    0.01
    Negative Logits
    abee
    -1.00
    nings
    -0.87
    ween
    -0.81
    zn
    -0.81
    abase
    -0.80
     showc
    -0.78
     misunder
    -0.73
    abo
    -0.73
    apo
    -0.72
    roman
    -0.71
    POSITIVE LOGITS
    èĢħ
    0.80
    é¾įå¥ij士
    0.74
    llor
    0.70
     Patricia
    0.69
     Corruption
    0.69
     Massive
    0.66
     Mankind
    0.66
     Justice
    0.65
     Frontier
    0.65
    ãĥĬ
    0.65
    Activations Density 0.052%

    No Known Activations