© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18487
    Prev
    Next
    INDEX
    Explanations

    words or phrases containing the prefix "sub-"

    oai_token-act-pair · gpt-3.5-turbo

    references to subcategories or subgroups

    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
     Barron
    -0.70
     sorely
    -0.66
    owing
    -0.65
     Jenner
    -0.64
     Dol
    -0.63
     Monk
    -0.63
     Sanford
    -0.62
    esome
    -0.62
     Loll
    -0.60
     Dickinson
    -0.60
    POSITIVE LOGITS
    Saharan
    1.37
    surface
    1.36
    division
    1.24
    committee
    1.21
    national
    1.20
    contract
    1.20
    continental
    1.18
    sections
    1.18
    zero
    1.15
    species
    1.14
    Activations Density 0.038%

    No Known Activations