© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 28808
    Prev
    Next
    INDEX
    Explanations

    references to witches and witch-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    420
    +0.12
    0.5%
    99
    +0.11
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.12
    0.01
    288
    +0.11
    0.01
    420
    +0.10
    0.01
    Negative Logits
    oulos
    -0.76
    ional
    -0.71
    ettel
    -0.71
    raits
    -0.65
    ity
    -0.63
    RAW
    -0.62
     embarrassment
    -0.59
    ateral
    -0.59
     scrimmage
    -0.58
     horizont
    -0.58
    POSITIVE LOGITS
    doctor
    1.40
    craft
    1.08
    finder
    1.03
    crow
    1.02
     haz
    1.01
    hunt
    1.00
     Hazel
    1.00
    blade
    0.94
    hunter
    0.88
    tail
    0.87
    Activations Density 0.067%

    No Known Activations