© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21117
    Prev
    Next
    INDEX
    Explanations

    contact information like email addresses, phone numbers, and addresses

    oai_token-act-pair · gpt-3.5-turbo

    contact information and organizational details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     objectively
    -0.71
    ixel
    -0.70
     progresses
    -0.68
     WATCHED
    -0.67
     sparing
    -0.67
     predictably
    -0.67
     experimented
    -0.66
     unpredict
    -0.65
    oiler
    -0.65
     unsurprisingly
    -0.64
    POSITIVE LOGITS
    Fax
    1.58
    Phone
    1.37
     Telephone
    1.28
    Tel
    1.27
     Phone
    1.26
     fax
    1.24
    Email
    1.24
     Email
    1.19
    email
    1.17
    Tele
    1.17
    Activations Density 0.195%

    No Known Activations