Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 3263
    Prev
    Next
    INDEX
    Explanations

    instances when someone lets the speaker know that a particular event occurred

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.75
    tre
    -0.71
    pher
    -0.66
    ios
    -0.64
    ________________________________
    -0.64
     Wend
    -0.63
    ccess
    -0.63
     Valerie
    -0.62
    elia
    -0.60
    uckle
    -0.59
    POSITIVE LOGITS
    doi
    0.77
    Downloadha
    0.75
    ivably
    0.73
    astical
    0.73
    urated
    0.72
    bath
    0.70
    ewski
    0.69
    bats
    0.69
    resy
    0.67
    orously
    0.65
    Activations Density 0.000%

    No Known Activations