© 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. 29624
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols in writing

    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
    68
    +0.14
    0.6%
    254
    +0.13
    0.6%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.14
    0.17
    43
    +0.13
    0.12
    546
    +0.10
    0.10
    Negative Logits
     Its
    -0.70
    itiz
    -0.67
    ocracy
    -0.64
    mie
    -0.63
     its
    -0.63
    west
    -0.63
    amus
    -0.63
    Its
    -0.61
    onement
    -0.60
    isine
    -0.60
    POSITIVE LOGITS
     ones
    1.51
    those
    1.38
     those
    1.07
    These
    1.06
    these
    1.05
     These
    1.02
     cylinders
    1.00
     replacements
    0.96
     Ones
    0.93
     respectively
    0.92
    Activations Density 1.794%

    No Known Activations