© 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. 10436
    Prev
    Next
    INDEX
    Explanations

    phone numbers in various formats

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and contact information

    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
     Ging
    -0.59
     dod
    -0.57
     fierce
    -0.56
     handcuffs
    -0.55
     polyg
    -0.55
    iping
    -0.55
     circumst
    -0.55
     Vital
    -0.54
     snowball
    -0.54
     alphabet
    -0.54
    POSITIVE LOGITS
    00
    1.07
    89
    1.02
    86
    1.02
    88
    1.01
    81
    0.98
    22
    0.97
    99
    0.97
    61
    0.96
    93
    0.96
    71
    0.96
    Activations Density 0.034%

    No Known Activations