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. 19543
    Prev
    Next
    INDEX
    Explanations

    terms related to historical contexts and cultural aspects

    oai_token-act-pair · gpt-3.5-turbo

    references to historical context and accounts

    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
    lain
    -1.00
    ertodd
    -0.98
    geon
    -0.84
    nery
    -0.84
    DAQ
    -0.82
    igans
    -0.77
    loo
    -0.77
    Flow
    -0.76
    ricular
    -0.75
    wich
    -0.71
    POSITIVE LOGITS
    orical
    0.94
     precedent
    0.94
     significance
    0.93
     revision
    0.90
    orically
    0.85
     preced
    0.84
     relics
    0.84
     preservation
    0.83
     inaccur
    0.83
     context
    0.83
    Activations Density 0.042%

    No Known Activations