© 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. 6-RES-JB
    11. 9483
    Prev
    Next
    INDEX
    Explanations

    words related to asserting or emphasizing a point

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "insist" and its variants

    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
    gone
    -0.88
    NetMessage
    -0.71
    sung
    -0.70
    brance
    -0.66
    xual
    -0.65
    anon
    -0.65
    ________________
    -0.65
    ammy
    -0.64
    izons
    -0.62
    ãĥŃ
    -0.62
    POSITIVE LOGITS
    ently
    0.99
    ially
    0.94
    antly
    0.85
     vehemently
    0.80
     adherence
    0.79
    iago
    0.75
    ively
    0.75
    enance
    0.75
    encies
    0.74
    iary
    0.72
    Activations Density 0.026%

    No Known Activations