© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4363
    Prev
    Next
    INDEX
    Explanations

    words related to loudness or volume

    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
    679
    +0.14
    0.6%
    365
    +0.12
    0.5%
    677
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.14
    0.01
    232
    +0.12
    0.01
    201
    +0.11
    0.01
    Negative Logits
     Deity
    -0.69
    xon
    -0.68
    coni
    -0.63
    ptives
    -0.63
    vasive
    -0.62
    Constructed
    -0.62
    poral
    -0.61
     Pax
    -0.60
    adelphia
    -0.60
    utics
    -0.59
    POSITIVE LOGITS
    oun
    1.01
    reau
    0.98
    spe
    0.95
    geoning
    0.85
    iquette
    0.84
    imentary
    0.81
    NESS
    0.81
    eh
    0.77
    ensity
    0.77
    emouth
    0.77
    Activations Density 0.048%

    No Known Activations