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. 7-RES-JB
    6. 15454
    Prev
    Next
    INDEX
    Explanations

    requests or demands from individuals to others

    oai_token-act-pair · gpt-3.5-turbo

    directives or commands related to leaving or taking action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +)
    -0.68
    uitive
    -0.68
     littered
    -0.65
    erie
    -0.62
     anecd
    -0.62
     hallmark
    -0.61
     arenas
    -0.59
     expands
    -0.59
     economies
    -0.59
     overlap
    -0.58
    POSITIVE LOGITS
     ASAP
    0.97
     tomorrow
    0.69
    quit
    0.67
     sometime
    0.66
     urgently
    0.65
    pez
    0.64
    ãĥĩ
    0.63
    escription
    0.62
     lest
    0.61
    omore
    0.61
    Activations Density 0.840%

    No Known Activations