© 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 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. 8-RES-JB
    11. 3858
    Prev
    Next
    INDEX
    Explanations

    conjunctions or contrasting phrases

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but" indicating contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enced
    -0.60
     Orient
    -0.55
    eah
    -0.55
    naire
    -0.55
    psy
    -0.53
     encyclopedia
    -0.53
     Corps
    -0.53
    urated
    -0.52
    resa
    -0.52
     Rolls
    -0.51
    POSITIVE LOGITS
    chery
    1.15
    tons
    1.12
    chers
    1.06
     nonetheless
    0.99
     nevertheless
    0.97
     alas
    0.85
    ts
    0.84
    ters
    0.83
    tered
    0.81
    ler
    0.80
    Activations Density 0.086%

    No Known Activations