© 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. 4-RES-JB
    11. 19563
    Prev
    Next
    INDEX
    Explanations

    the word "can" followed by an action or description

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "I can"

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

    No Comments

    Negative Logits
     guarding
    -0.63
     revision
    -0.62
     Mant
    -0.61
     danger
    -0.60
     Hunters
    -0.60
     Rising
    -0.60
     rejection
    -0.59
    edient
    -0.59
     Federation
    -0.59
    bats
    -0.57
    POSITIVE LOGITS
    't
    1.61
    adian
    1.22
    berra
    1.17
    NOT
    1.06
    tera
    1.00
    isters
    0.91
    ¶ħ
    0.87
    opy
    0.87
    vas
    0.85
     attest
    0.84
    Activations Density 0.157%

    No Known Activations