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. 10-RES-JB
    6. 23988
    Prev
    Next
    INDEX
    Explanations

    phrases where someone or something is being identified or identifying itself/herself/himself

    oai_token-act-pair · gpt-3.5-turbo

    words related to identification and self-identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fare
    -0.85
    ework
    -0.77
    mare
    -0.69
    orah
    -0.67
    ocracy
    -0.66
    hetti
    -0.64
    aptic
    -0.63
    umblr
    -0.63
    wake
    -0.62
    orld
    -0.62
    POSITIVE LOGITS
    ively
    0.78
    pointers
    0.76
     ourselves
    0.70
     themselves
    0.68
    acons
    0.66
    ibly
    0.65
     shortcomings
    0.64
     weaknesses
    0.64
    ifiable
    0.64
     identifying
    0.63
    Activations Density 0.043%

    No Known Activations