© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2838
    Prev
    Next
    INDEX
    Explanations

    words related to pointing out or noting something in a statement or argument

    oai_token-act-pair · gpt-3.5-turbo

    reports or statements that reference observations or notes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quer
    -0.74
    nect
    -0.72
    endar
    -0.68
    ãĥİ
    -0.67
    channelAvailability
    -0.66
    scribe
    -0.63
    ctions
    -0.63
    awaru
    -0.63
    ctors
    -0.63
    MAS
    -0.63
    POSITIVE LOGITS
     similarities
    1.13
     that
    1.08
     how
    1.07
     inconsistencies
    0.98
     discrepancies
    0.95
     shortcomings
    0.89
     differences
    0.87
    that
    0.85
     flaws
    0.85
     deficiencies
    0.83
    Activations Density 0.092%

    No Known Activations