© 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. 6-RES-JB
    11. 2699
    Prev
    Next
    INDEX
    Explanations

    actions or initiatives being extended or expanded

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "extend"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fighter
    -0.80
    tery
    -0.78
    ches
    -0.78
    lins
    -0.71
    Submit
    -0.70
    lean
    -0.70
    idding
    -0.69
    powder
    -0.69
    girls
    -0.69
    ids
    -0.69
    POSITIVE LOGITS
     adolesc
    1.06
     warranties
    0.93
     cord
    0.79
     cords
    0.79
    ENDED
    0.76
     extended
    0.74
     lifespan
    0.72
     ende
    0.72
     maturity
    0.71
    ITED
    0.71
    Activations Density 0.026%

    No Known Activations