© 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. 1-RES-JB
    11. 20245
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the action of "putting" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.92
    SPONSORED
    -0.73
    ĨĴ
    -0.61
    VEL
    -0.59
     agile
    -0.58
    andon
    -0.58
    antz
    -0.57
     Oaks
    -0.56
    scripts
    -0.56
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.55
    POSITIVE LOGITS
    put
    1.07
    TING
    1.03
    ting
    0.91
    ters
    0.89
    ongh
    0.80
    ted
    0.80
    tered
    0.80
    ronics
    0.79
     MSG
    0.78
    aneously
    0.78
    Activations Density 0.009%

    No Known Activations