© 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. 10183
    Prev
    Next
    INDEX
    Explanations

    negative statements or denials

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of absence

    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
    Js
    -0.75
    ean
    -0.74
    eals
    -0.73
    alde
    -0.72
    rs
    -0.72
    ents
    -0.70
    rn
    -0.69
    lish
    -0.69
    agents
    -0.68
    rand
    -0.67
    POSITIVE LOGITS
     shortage
    1.35
     doubt
    1.28
     indication
    1.18
     reason
    1.11
     denying
    1.06
     guarantee
    1.05
     excuse
    1.05
     ambiguity
    1.01
     difference
    0.97
     timetable
    0.96
    Activations Density 0.074%

    No Known Activations