© 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. 7-RES-JB
    11. 9938
    Prev
    Next
    INDEX
    Explanations

    sentences with legal or formal terms

    oai_token-act-pair · gpt-3.5-turbo

    film-related terminology and discussions around adaptations and productions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *.
    -0.61
    entimes
    -0.61
    ypes
    -0.60
    =]
    -0.57
    patch
    -0.57
    -"
    -0.55
    ede
    -0.55
    omever
    -0.54
    none
    -0.54
    venth
    -0.54
    POSITIVE LOGITS
     also
    0.57
     Corker
    0.56
     tackles
    0.56
     quietly
    0.55
     GOODMAN
    0.55
     Heb
    0.55
     apologised
    0.54
     hailed
    0.54
    atories
    0.54
     divided
    0.54
    Activations Density 0.832%

    No Known Activations