© 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. 4-RES-JB
    11. 2098
    Prev
    Next
    INDEX
    Explanations

    instances where a call is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "call" in various contexts

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

    No Comments

    Negative Logits
     concentration
    -0.71
    theless
    -0.70
     incorpor
    -0.66
     Fiction
    -0.65
     decomp
    -0.65
    izontal
    -0.64
     centrif
    -0.64
     ferment
    -0.62
    afort
    -0.61
    aced
    -0.60
    POSITIVE LOGITS
    backs
    1.25
    call
    1.07
    igraph
    0.92
     caller
    0.84
    outs
    0.84
     calls
    0.83
     911
    0.80
    oused
    0.79
    cards
    0.78
     calling
    0.78
    Activations Density 0.033%

    No Known Activations