© 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. 6-RES-JB
    11. 2563
    Prev
    Next
    INDEX
    Explanations

    references to receiving or making phone calls

    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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concentration
    -0.74
     Fiction
    -0.73
     ferment
    -0.64
     Flavoring
    -0.64
    afort
    -0.61
     stocking
    -0.61
     inh
    -0.60
    izontal
    -0.60
     marginal
    -0.59
     Classes
    -0.58
    POSITIVE LOGITS
    backs
    1.22
    igraph
    1.11
    call
    1.08
    oused
    0.89
    calling
    0.88
     caller
    0.86
    outs
    0.81
    aghan
    0.81
     911
    0.78
    externalActionCode
    0.76
    Activations Density 0.042%

    No Known Activations