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. 9-RES-JB
    6. 6493
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing examples or explanations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neutrality
    -0.62
     premature
    -0.56
     idol
    -0.55
     anch
    -0.55
     objectives
    -0.53
     stray
    -0.53
     trophies
    -0.52
     cha
    -0.52
     stewards
    -0.52
     appropri
    -0.51
    POSITIVE LOGITS
    g
    1.01
     coli
    0.95
    gger
    0.89
    eg
    0.87
    e
    0.82
    gart
    0.82
    fter
    0.77
    hart
    0.77
    viously
    0.76
    gas
    0.75
    Activations Density 0.020%

    No Known Activations