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. 8671
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Whit" with varying levels of activation, potentially indicating a focus on names or entities related to "Whit."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Whit."

    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
    anwhile
    -0.91
    PsyNetMessage
    -0.89
    igslist
    -0.82
    aeda
    -0.82
    Pg
    -0.78
    ournal
    -0.74
     confir
    -0.70
    raltar
    -0.70
    Downloadha
    -0.69
    orsi
    -0.68
    POSITIVE LOGITS
    ewater
    1.27
    bread
    1.14
    eness
    1.05
    robe
    1.03
    ening
    1.02
    comb
    1.02
    ney
    0.99
    ened
    0.98
    acre
    0.97
    eless
    0.96
    Activations Density 0.005%

    No Known Activations