© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1753
    Prev
    Next
    INDEX
    Explanations

    references to citations, questions, or instructions in a document

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically closing parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cra
    -0.79
    anyl
    -0.76
    ©¶æ
    -0.71
     thrott
    -0.70
     hoard
    -0.67
    ĪĴ
    -0.66
     crate
    -0.63
     computing
    -0.63
     deliber
    -0.63
     transition
    -0.62
    POSITIVE LOGITS
     Anyway
    1.19
     Similarly
    0.92
     Interestingly
    0.92
     Conversely
    0.92
     Therefore
    0.90
     Originally
    0.87
    <|endoftext|>
    0.87
     Alternatively
    0.87
     ********************************
    0.86
    ↵Âł
    0.86
    Activations Density 0.113%

    No Known Activations