© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24318
    Prev
    Next
    INDEX
    Explanations

    phrases related to causation or the underlying essence of actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating essential or fundamental concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    20439
    -0.82
     preferably
    -0.74
     evidently
    -0.73
     surely
    -0.73
     undoubtedly
    -0.73
    often
    -0.71
     frequently
    -0.71
     moreover
    -0.70
    particularly
    -0.70
     doubtless
    -0.69
    POSITIVE LOGITS
     shorthand
    0.75
     inverse
    0.74
     reinvent
    0.68
    NetMessage
    0.67
     Frankenstein
    0.67
    reverse
    0.65
    enegger
    0.65
     Manson
    0.65
    Fuck
    0.64
     Canaver
    0.64
    Activations Density 0.319%

    No Known Activations