© 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. 9-RES-JB
    11. 17089
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific roles or positions in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to organizational roles or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -0.74
     Cavern
    -0.71
     Legions
    -0.69
     Kingdoms
    -0.66
    iths
    -0.63
    edes
    -0.63
    ackers
    -0.63
     largeDownload
    -0.62
    itives
    -0.61
     Hig
    -0.59
    POSITIVE LOGITS
    wide
    1.06
     assignment
    0.79
     designation
    0.77
    ouver
    0.75
     outing
    0.75
     affiliation
    0.73
     diary
    0.72
     adjustment
    0.71
     colleague
    0.71
     portrait
    0.71
    Activations Density 0.564%

    No Known Activations