© 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. 13155
    Prev
    Next
    INDEX
    Explanations

    proper nouns, such as names of people, places, and brands

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals associated with creative works

    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
    wered
    -0.74
     refusal
    -0.68
     silence
    -0.68
    ghazi
    -0.67
    bledon
    -0.66
    stood
    -0.65
     constitu
    -0.64
     whine
    -0.63
    VERTISEMENT
    -0.62
     denial
    -0.62
    POSITIVE LOGITS
     Architects
    1.09
    iets
    0.91
     Productions
    0.87
     Associates
    0.86
     himself
    0.85
     respectively
    0.84
     (@
    0.77
     Himself
    0.77
     Studios
    0.75
     aka
    0.75
    Activations Density 0.282%

    No Known Activations