© 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. 2765
    Prev
    Next
    INDEX
    Explanations

    names and initials associated with people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and significant names

    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
     Bots
    -0.78
     Cody
    -0.76
     Vera
    -0.75
    avorite
    -0.73
    ãĥ¯
    -0.71
     metic
    -0.70
    ortunately
    -0.70
     warr
    -0.68
    ĸļ
    -0.67
     earthqu
    -0.67
    POSITIVE LOGITS
    ^
    0.88
    iac
    0.79
    ais
    0.76
    uth
    0.75
    HY
    0.75
    UCT
    0.75
    aug
    0.73
    agram
    0.73
    oyal
    0.72
    alle
    0.72
    Activations Density 0.233%

    No Known Activations