© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29979
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "all"

    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
    393
    +0.12
    0.6%
    1
    +0.11
    0.5%
    735
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.12
    0.09
    237
    +0.11
    0.07
    637
    +0.10
    0.08
    Negative Logits
    potion
    -0.69
    aminer
    -0.65
    gee
    -0.60
    IND
    -0.60
     somew
    -0.58
     nowhere
    -0.58
    yip
    -0.58
    rir
    -0.57
    ernaut
    -0.56
     Caption
    -0.56
    POSITIVE LOGITS
    ocating
    1.41
    usions
    1.21
     kinds
    1.19
     sorts
    1.17
    ocations
    1.16
    ocated
    1.14
    oys
    1.10
    igators
    1.10
    ocate
    1.09
    owing
    1.09
    Activations Density 0.415%

    No Known Activations