© 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. 7-RES-JB
    11. 1738
    Prev
    Next
    INDEX
    Explanations

    information attributed to spokespersons or representatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "for," indicating a focus on spokesperson roles and attributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    eat
    -0.73
    entry
    -0.68
    floor
    -0.64
    Stud
    -0.64
    Congratulations
    -0.63
    utterstock
    -0.63
    rooms
    -0.63
    NULL
    -0.62
    bone
    -0.62
     nightmares
    -0.62
    POSITIVE LOGITS
    bidden
    0.82
     Attorney
    0.77
     Gov
    0.76
     spokesperson
    0.73
     ITV
    0.72
     Universal
    0.72
     Libre
    0.68
     Cause
    0.67
     spokesman
    0.67
     prosecuting
    0.66
    Activations Density 0.056%

    No Known Activations