© 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. 8-RES-JB
    11. 3257
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "call"

    oai_token-act-pair · gpt-3.5-turbo

    references to phone calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.71
     Fiction
    -0.67
     colon
    -0.64
     embr
    -0.63
     bunny
    -0.63
     coat
    -0.62
     inh
    -0.61
     Coat
    -0.61
     bat
    -0.61
     ferment
    -0.60
    POSITIVE LOGITS
    backs
    1.18
    igraph
    1.15
    call
    1.02
    calling
    0.89
    oused
    0.88
     caller
    0.80
    outs
    0.79
    ouses
    0.76
    tower
    0.73
    graph
    0.73
    Activations Density 0.042%

    No Known Activations