© 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. 12-RES-JB
    11. 3961
    Prev
    Next
    INDEX
    Explanations

    names of celebrities, especially those starting with the letter "J"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to certain celebrities or well-known figures, particularly those with the initial 'J'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     thirds
    -0.71
     late
    -0.66
     delays
    -0.65
     doubling
    -0.65
     captcha
    -0.65
     granting
    -0.64
     paving
    -0.63
     alternating
    -0.61
     cancelled
    -0.61
     delaying
    -0.61
    POSITIVE LOGITS
    ealous
    1.25
    igsaw
    1.25
    ules
    1.24
    aden
    1.22
    ASON
    1.19
    abba
    1.16
    EFF
    1.15
    odi
    1.15
    AMES
    1.09
    YP
    1.09
    Activations Density 0.028%

    No Known Activations