© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7467
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences emphasizing the exclusivity or uniqueness of something

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases emphasizing limitations or conditions related to "only"

    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
    ducers
    -0.68
    hement
    -0.68
    ne
    -0.64
    ongs
    -0.64
    alam
    -0.64
    idon
    -0.63
    psc
    -0.63
    wealth
    -0.63
    tails
    -0.61
    rigan
    -0.60
    POSITIVE LOGITS
     marginally
    1.17
     kidding
    0.83
     partially
    0.82
     accessible
    0.82
     scratched
    0.80
     slightly
    0.77
     moderately
    0.76
     halfway
    0.75
     temporary
    0.74
     scratching
    0.74
    Activations Density 0.054%

    No Known Activations