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. 9-RES-JB
    6. 22242
    Prev
    Next
    INDEX
    Explanations

    terms related to technological concepts, specifically from the field of computing and information technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governance and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fielder
    -0.69
     attacker
    -0.60
     interpreter
    -0.56
     accompanying
    -0.56
     Houth
    -0.54
     interviewer
    -0.53
     affidavit
    -0.53
     rover
    -0.52
     dentist
    -0.52
     undisclosed
    -0.51
    POSITIVE LOGITS
    arenthood
    0.96
    thood
    0.88
    iculture
    0.83
    opia
    0.77
    livion
    0.76
    ankind
    0.75
    asonry
    0.75
    politics
    0.73
    ogenesis
    0.73
    ivism
    0.72
    Activations Density 0.973%

    No Known Activations