© 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. 3-RES-JB
    11. 18489
    Prev
    Next
    INDEX
    Explanations

    words related to tapes or recordings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "tape."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ationally
    -0.76
    ancial
    -0.76
    Ĭ±
    -0.68
    ablishment
    -0.67
    姫
    -0.66
     Canary
    -0.66
    abad
    -0.65
    onsense
    -0.64
     Democr
    -0.63
    swers
    -0.63
    POSITIVE LOGITS
     tape
    1.13
     Tape
    1.09
     tapes
    0.99
     recorder
    0.95
    clip
    0.87
     cassette
    0.86
     taped
    0.85
     Tycoon
    0.75
    pered
    0.75
    face
    0.75
    Activations Density 0.009%

    No Known Activations