© 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. 3-RES-JB
    11. 12585
    Prev
    Next
    INDEX
    Explanations

    phone calls being made or requested in a narrative

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "call" and its variations, indicating requests for assistance or emergency responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inth
    -0.83
     Flavoring
    -0.73
    izontal
    -0.70
    Cub
    -0.67
    itars
    -0.67
    yrinth
    -0.66
    theless
    -0.65
    _-
    -0.64
    ffiti
    -0.64
     concentration
    -0.63
    POSITIVE LOGITS
    call
    1.07
    backs
    0.93
     911
    0.91
     Call
    0.90
    igraph
    0.89
    Call
    0.82
     CALL
    0.77
     attention
    0.76
    calling
    0.75
     999
    0.73
    Activations Density 0.056%

    No Known Activations