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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 13453
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names like "Spencer" and "Sterling."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Spencer" and references to the name "Sterling"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arist
    -0.75
    juven
    -0.70
    LOAD
    -0.62
    trust
    -0.62
     catast
    -0.61
     advers
    -0.60
    usterity
    -0.59
     CFR
    -0.58
    avez
    -0.58
     burdens
    -0.58
    POSITIVE LOGITS
     Tracy
    0.90
     Spencer
    0.86
    cil
    0.83
    itta
    0.79
    chell
    0.77
    ENCE
    0.76
    ville
    0.75
    onite
    0.75
    olson
    0.73
    otle
    0.73
    Activations Density 0.024%

    No Known Activations