© 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. 9-RES-JB
    11. 11731
    Prev
    Next
    INDEX
    Explanations

    evaluative or opinion-based phrases about people or things

    oai_token-act-pair · gpt-3.5-turbo

    words related to evaluations and judgments, such as praise, criticism, and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.63
     Conversation
    -0.59
    rouse
    -0.59
     Same
    -0.57
    abiding
    -0.57
    Exit
    -0.57
     Wave
    -0.56
    acion
    -0.56
    mad
    -0.56
     reckoning
    -0.55
    POSITIVE LOGITS
     by
    0.90
     unfairly
    0.89
     extensively
    0.84
     unanimously
    0.79
     skept
    0.77
    igated
    0.76
     controvers
    0.76
     repeatedly
    0.75
     harshly
    0.73
     internationally
    0.73
    Activations Density 0.180%

    No Known Activations