© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2709
    Prev
    Next
    INDEX
    Explanations

    contact information such as phone numbers and emails

    oai_token-act-pair · gpt-3.5-turbo

    contact information, particularly phone numbers and formats

    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
     regimes
    -0.64
     unrel
    -0.61
    escape
    -0.60
    sic
    -0.60
     sucker
    -0.60
     seal
    -0.58
     stacking
    -0.57
     flavours
    -0.56
     feast
    -0.55
     accompanying
    -0.54
    POSITIVE LOGITS
    704
    0.69
     ILCS
    0.68
     403
    0.68
    423
    0.67
     408
    0.67
     503
    0.66
    685
    0.66
    669
    0.66
     978
    0.65
     407
    0.65
    Activations Density 0.021%

    No Known Activations