© 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. 14361
    Prev
    Next
    INDEX
    Explanations

    commands or instructions related to coding and programming

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and references to sequences or processes

    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
    hoe
    -0.80
    spir
    -0.78
    poke
    -0.71
    justice
    -0.69
    pell
    -0.67
    illian
    -0.64
    lav
    -0.64
    ãĥĵ
    -0.64
    utch
    -0.63
    acus
    -0.63
    POSITIVE LOGITS
     optionally
    1.54
     then
    1.35
     thus
    1.32
     hence
    1.31
     secondly
    1.30
     therefore
    1.27
     vice
    1.23
     consequently
    1.22
     thence
    1.20
     THEN
    1.17
    Activations Density 0.257%

    No Known Activations