© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 12335
    Prev
    Next
    INDEX
    Explanations

    words related to text or document 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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzle
    -0.77
    vil
    -0.68
    ju
    -0.67
    ggle
    -0.67
    jab
    -0.67
    resy
    -0.66
    yu
    -0.65
    ³³³³³³³³³³³³³³³³
    -0.65
     Vengeance
    -0.65
    deen
    -0.63
    POSITIVE LOGITS
     Transcript
    1.48
     transcript
    1.37
     transcripts
    1.34
     transcription
    1.01
     excerpts
    0.84
    icons
    0.83
    ions
    0.79
     tapes
    0.78
     TRAN
    0.78
     snippets
    0.77
    Activations Density 0.017%

    No Known Activations