© 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. 9-RES-JB
    11. 1022
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and coding, specifically focusing on variable names, code snippets, and syntax

    oai_token-act-pair · gpt-3.5-turbo

    references to programming concepts and user data structures

    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
     magnets
    -0.70
     arteries
    -0.69
     sclerosis
    -0.63
     relativity
    -0.63
     biodiversity
    -0.63
    itably
    -0.63
     Canaveral
    -0.60
     corridors
    -0.59
     poaching
    -0.58
     Kling
    -0.57
    POSITIVE LOGITS
    -$
    1.08
    ['
    1.06
     eq
    0.98
    /$
    0.94
    $.
    0.89
    Container
    0.88
    $,
    0.88
    rc
    0.87
    USER
    0.87
    $
    0.87
    Activations Density 0.067%

    No Known Activations