© 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. 11183
    Prev
    Next
    INDEX
    Explanations

    negative statements indicating something has not occurred or been completed yet

    oai_token-act-pair · gpt-3.5-turbo

    negations or instances of being unfulfilled or absent

    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
    CRIP
    -0.71
     Pair
    -0.65
     Spectrum
    -0.64
    EEP
    -0.63
     Must
    -0.62
     Older
    -0.62
     Digest
    -0.62
     Rouge
    -0.61
    href
    -0.58
    rift
    -0.58
    POSITIVE LOGITS
     yet
    1.38
     been
    1.24
    yet
    1.21
     gotten
    1.10
    hin
    1.08
    been
    1.07
    epad
    1.02
    icably
    1.00
     hesitated
    0.99
     fared
    0.98
    Activations Density 0.061%

    No Known Activations