© 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. 5523
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change or transition

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "come into" along with significant events or transitions

    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
    killer
    -0.63
    tan
    -0.59
    cham
    -0.59
     DMCA
    -0.58
    uploads
    -0.56
    copy
    -0.55
    %"
    -0.55
    ļéĨĴ
    -0.55
     snail
    -0.55
    upload
    -0.54
    POSITIVE LOGITS
     fruition
    0.99
     adulthood
    0.81
    abeth
    0.81
     prominence
    0.79
     fray
    0.78
    jected
    0.75
    operative
    0.75
    ital
    0.74
     contact
    0.68
     orbit
    0.66
    Activations Density 0.030%

    No Known Activations