© 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. 9-RES-JB
    11. 18405
    Prev
    Next
    INDEX
    Explanations

    keywords related to negation, prohibition, or rejection

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "any" in various contexts

    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
    rex
    -0.86
    gypt
    -0.81
    staking
    -0.76
    rez
    -0.72
     Originally
    -0.70
    romy
    -0.70
    expensive
    -0.69
    raid
    -0.68
    itals
    -0.67
    artments
    -0.66
    POSITIVE LOGITS
     semblance
    1.14
    THING
    1.13
     conceivable
    1.08
     attempt
    1.01
     resemblance
    0.98
     kind
    0.95
    WHERE
    0.95
     deviation
    0.93
    body
    0.92
     meaningful
    0.91
    Activations Density 0.079%

    No Known Activations