© 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. 10-RES-JB
    11. 13775
    Prev
    Next
    INDEX
    Explanations

    words related to communication, such as "signal."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to signaling in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erenn
    -0.74
    sm
    -0.73
    venge
    -0.72
    uum
    -0.71
    yright
    -0.71
    jury
    -0.70
    spell
    -0.68
    amily
    -0.66
     Roof
    -0.64
    ighth
    -0.64
    POSITIVE LOGITS
     signals
    1.04
     handlers
    1.00
     emanating
    0.99
     handler
    0.95
     signal
    0.94
     reinforcement
    0.84
     emitted
    0.83
     blocker
    0.83
     signaling
    0.82
     overload
    0.82
    Activations Density 0.038%

    No Known Activations