© 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. 20645
    Prev
    Next
    INDEX
    Explanations

    phone numbers and contact information

    oai_token-act-pair · gpt-3.5-turbo

    references to contact information and phone numbers

    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
    BIP
    -0.68
    weights
    -0.66
     RAID
    -0.66
     WATCHED
    -0.66
     clips
    -0.65
     narrator
    -0.61
    worthiness
    -0.60
    ¥µ
    -0.60
     hypoc
    -0.59
     rounds
    -0.58
    POSITIVE LOGITS
     212
    1.16
    877
    1.14
     503
    1.12
    Phone
    1.11
     303
    1.08
     415
    1.08
     800
    1.08
     317
    1.08
     407
    1.06
     608
    1.06
    Activations Density 0.113%

    No Known Activations