© 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. 4-RES-JB
    11. 18461
    Prev
    Next
    INDEX
    Explanations

    text related to transcripts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "transcript."

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

    No Comments

    Negative Logits
    ³³³³³³³³³³³³³³³³
    -0.68
    ggle
    -0.68
    yu
    -0.68
    vil
    -0.67
     Geh
    -0.66
    zzle
    -0.64
    pton
    -0.63
    pper
    -0.62
    ignment
    -0.61
     Slug
    -0.61
    POSITIVE LOGITS
     Transcript
    1.31
     transcripts
    1.24
     transcript
    1.22
     transcription
    1.04
     snippets
    0.83
    ophon
    0.80
     transc
    0.78
    ophone
    0.78
     excerpts
    0.76
    ions
    0.75
    Activations Density 0.022%

    No Known Activations