© 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. 10-RES-JB
    11. 10192
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "phone" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to phone calls and communication

    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
    ulpt
    -0.78
    redits
    -0.77
     ItemLevel
    -0.76
    orthy
    -0.76
    artifacts
    -0.74
    oiler
    -0.73
     galleries
    -0.71
    ilib
    -0.70
     biome
    -0.69
     sculpt
    -0.69
    POSITIVE LOGITS
     voic
    1.95
     phone
    1.82
     telephone
    1.81
     caller
    1.75
     Telephone
    1.67
    phone
    1.67
     phones
    1.62
     Phone
    1.59
     cellphone
    1.53
    Phone
    1.51
    Activations Density 0.487%

    No Known Activations