© 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. 6-RES-JB
    11. 23275
    Prev
    Next
    INDEX
    Explanations

    the word "assert" as well as related concepts and actions

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "assert" and related expressions of assertion or confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carbuncle
    -0.76
    ppo
    -0.70
     Bake
    -0.67
    bies
    -0.66
    shows
    -0.66
     Watching
    -0.64
    nton
    -0.63
    fell
    -0.63
    oho
    -0.63
    MET
    -0.62
    POSITIVE LOGITS
    ively
    1.00
    iveness
    0.94
    uable
    0.90
    uably
    0.89
    antly
    0.88
    ive
    0.87
    ements
    0.85
    ieth
    0.85
    olated
    0.84
    ially
    0.82
    Activations Density 0.030%

    No Known Activations