© 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. 11679
    Prev
    Next
    INDEX
    Explanations

    first person singular personal pronouns

    oai_token-act-pair · gpt-3.5-turbo

    statements of personal experience or sentiment

    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
    ahime
    -0.70
     ubiqu
    -0.66
     diam
    -0.66
    ruary
    -0.60
    uyomi
    -0.60
    Origin
    -0.59
     simultane
    -0.59
    mart
    -0.58
    artisan
    -0.58
    eday
    -0.58
    POSITIVE LOGITS
     ever
    0.96
     needed
    0.85
     fuss
    0.85
     cared
    0.84
     mattered
    0.83
    soever
    0.79
     EVER
    0.78
     cares
    0.76
     can
    0.75
     wanted
    0.72
    Activations Density 0.070%

    No Known Activations