© 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. 1060
    Prev
    Next
    INDEX
    Explanations

    names and terms related to individuals involved in political and legal controversies

    oai_token-act-pair · gpt-3.5-turbo

    names of people and specific individuals associated with events

    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
     Blizz
    -0.83
    ahime
    -0.77
    iculture
    -0.76
     Jagu
    -0.75
     rugby
    -0.74
     Welsh
    -0.74
     relegation
    -0.73
     regeneration
    -0.72
     guiActiveUnfocused
    -0.72
     WCS
    -0.71
    POSITIVE LOGITS
    arnaev
    1.21
    FBI
    1.13
     FBI
    0.93
     Tsarnaev
    0.93
     spying
    0.93
    ileaks
    0.92
    terrorist
    0.89
    Qaeda
    0.88
    ghazi
    0.87
    CIA
    0.87
    Activations Density 0.328%

    No Known Activations