© 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. 7600
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "directly" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "directly."

    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
    gerald
    -0.82
    glers
    -0.79
     Garry
    -0.73
     Daily
    -0.68
     Scor
    -0.66
     Boys
    -0.66
     Kirin
    -0.66
     Millennium
    -0.66
     Killer
    -0.65
    ulton
    -0.65
    POSITIVE LOGITS
     contradicted
    0.91
     identifiable
    0.86
     contradicts
    0.81
     contradict
    0.80
     benefited
    0.76
    cedented
    0.75
     direct
    0.71
     addressed
    0.71
     attributable
    0.71
     confront
    0.70
    Activations Density 0.017%

    No Known Activations