© 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. 9-RES-JB
    11. 16030
    Prev
    Next
    INDEX
    Explanations

    comparative terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "equally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.73
    ocene
    -0.73
    uese
    -0.72
     Tie
    -0.70
     Coff
    -0.66
     Buy
    -0.65
    ourke
    -0.65
     Vu
    -0.65
     Jackets
    -0.64
    Query
    -0.64
    POSITIVE LOGITS
     sized
    1.01
     situated
    0.93
     weighted
    0.89
     spaced
    0.89
     applicable
    0.89
     important
    0.88
     impressive
    0.83
     adept
    0.83
     emph
    0.81
     nause
    0.80
    Activations Density 0.026%

    No Known Activations