© 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. 10-RES-JB
    11. 3283
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or contact between individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to contact and communication with individuals

    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
    rawdownloadcloneembedreportprint
    -0.76
    Temperature
    -0.65
     ILCS
    -0.64
     dominates
    -0.60
     Execution
    -0.60
     Tsukuyomi
    -0.57
    edge
    -0.56
     consumed
    -0.55
     eaten
    -0.54
     Category
    -0.54
    POSITIVE LOGITS
     asking
    1.09
     requesting
    1.07
     regarding
    0.96
     privately
    0.94
     via
    0.93
     urgently
    0.92
     directly
    0.91
     inquire
    0.89
     anonymously
    0.89
     inappropriately
    0.88
    Activations Density 0.143%

    No Known Activations