© 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. 10-RES-JB
    11. 10780
    Prev
    Next
    INDEX
    Explanations

    the phrase "the only thing" followed by additional context

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the phrase "the only thing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onz
    -0.75
    ãĤ´ãĥ³
    -0.75
    perse
    -0.71
    lance
    -0.69
    enture
    -0.69
    baugh
    -0.69
    soon
    -0.68
    inate
    -0.67
     fixme
    -0.67
    analysis
    -0.67
    POSITIVE LOGITS
     missing
    0.95
     separating
    0.90
     bothering
    0.88
     happening
    0.88
     that
    0.87
     we
    0.86
     keeping
    0.83
     preventing
    0.82
     stopping
    0.82
     you
    0.81
    Activations Density 0.064%

    No Known Activations