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. 8-RES-JB
    6. 21567
    Prev
    Next
    INDEX
    Explanations

    names or words related to the surname "Karman"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "man" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.66
    fuel
    -0.64
    ombo
    -0.62
    ÃįÃį
    -0.62
    urus
    -0.62
    anked
    -0.60
    ignty
    -0.59
     fibre
    -0.58
    irlf
    -0.58
    respective
    -0.58
    POSITIVE LOGITS
    ifest
    1.38
    ufact
    1.14
    iac
    1.12
    ning
    1.11
    iasis
    1.07
    uscript
    1.05
    ned
    0.97
    hattan
    0.96
    士
    0.95
    oeuv
    0.94
    Activations Density 0.062%

    No Known Activations