© 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. 11449
    Prev
    Next
    INDEX
    Explanations

    contractions with apostrophes followed by the word 's

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "here's."

    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
    alties
    -0.79
    soever
    -0.71
    iac
    -0.68
    aneers
    -0.66
    anes
    -0.65
    esm
    -0.65
    nesota
    -0.61
    trust
    -0.61
    doms
    -0.61
    icc
    -0.60
    POSITIVE LOGITS
     hoping
    1.12
     another
    0.82
     why
    0.80
     how
    0.80
     excerpt
    0.80
     whats
    0.76
     what
    0.75
     yours
    0.73
     rundown
    0.72
     kicker
    0.70
    Activations Density 0.065%

    No Known Activations