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

    Neuronpedia

    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. 18900
    Prev
    Next
    INDEX
    Explanations

    technical terms or specific phrases related to programming or coding

    oai_token-act-pair · gpt-3.5-turbo

    recurring themes and significant elements within a narrative or discussion

    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
     Starts
    -0.62
     indefinitely
    -0.54
     Carney
    -0.52
    aples
    -0.51
    kefeller
    -0.51
    enegger
    -0.50
    velt
    -0.49
     Roots
    -0.49
     extrad
    -0.48
    erenn
    -0.48
    POSITIVE LOGITS
    }.
    0.89
    )).
    0.76
     etc
    0.67
    '.
    0.66
    .).
    0.65
    .</
    0.64
    >.
    0.63
    ?).
    0.63
    %.
    0.63
     thereto
    0.62
    Activations Density 1.600%

    No Known Activations