© 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 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. 0-RES-JB
    11. 12558
    Prev
    Next
    INDEX
    Explanations

    instances of the word "read" followed by a high activation value of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "read" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prop
    -0.68
     Nu
    -0.67
     van
    -0.66
     bot
    -0.66
     Villa
    -0.60
     caution
    -0.60
     horn
    -0.60
     legend
    -0.59
     harm
    -0.59
     lid
    -0.59
    POSITIVE LOGITS
    read
    4.22
    reads
    2.92
    reading
    2.63
    reader
    2.21
    READ
    1.93
     read
    1.86
    Read
    1.70
     Read
    1.57
     READ
    1.52
    Reading
    1.42
    Activations Density 0.017%

    No Known Activations