© 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. 11-RES-JB
    11. 20829
    Prev
    Next
    INDEX
    Explanations

    phrase that start with "Not" followed by an adjective or verb

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating something is less than expected or average

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etimes
    -0.82
    TIME
    -0.81
    aughs
    -0.72
    éĹĺ
    -0.71
    Ĥİ
    -0.70
    cki
    -0.67
    £ı
    -0.66
    llah
    -0.66
    metry
    -0.64
    WAY
    -0.63
    POSITIVE LOGITS
     terribly
    1.25
     overly
    1.25
     flashy
    1.24
     overpower
    1.16
    icably
    1.08
     terrible
    1.08
     necessarily
    1.06
     bad
    1.05
     particularly
    1.03
     excessively
    1.00
    Activations Density 0.151%

    No Known Activations