© 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. 9609
    Prev
    Next
    INDEX
    Explanations

    references to the word "Telegraph."

    oai_token-act-pair · gpt-3.5-turbo
    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
    regn
    -0.67
    java
    -0.66
     Salvador
    -0.65
     Dillon
    -0.64
    rior
    -0.64
    laws
    -0.63
    GD
    -0.62
    atri
    -0.62
    lahoma
    -0.62
     Garn
    -0.61
    POSITIVE LOGITS
    legraph
    1.09
    ic
    0.82
     Tycoon
    0.81
    orld
    0.81
    orial
    0.79
    ically
    0.79
    aic
    0.78
    shire
    0.78
    iership
    0.76
    ical
    0.76
    Activations Density 0.019%

    No Known Activations