© 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. 12-RES-JB
    11. 3132
    Prev
    Next
    INDEX
    Explanations

    instances of negation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    negative phrases that convey doubt or lack of validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ean
    -0.85
    redients
    -0.82
    eds
    -0.81
    views
    -0.81
    types
    -0.77
    inion
    -0.76
     Actions
    -0.76
    ULTS
    -0.76
    ents
    -0.76
    parts
    -0.75
    POSITIVE LOGITS
     shortage
    1.32
     denying
    1.30
     doubt
    1.26
     excuse
    1.14
     escaping
    1.14
     indication
    1.09
     guarantee
    1.09
     reason
    1.04
     question
    1.03
     way
    0.99
    Activations Density 0.078%

    No Known Activations