© 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. 7-RES-JB
    11. 2094
    Prev
    Next
    INDEX
    Explanations

    contradictory statements

    oai_token-act-pair · gpt-3.5-turbo

    questions regarding the necessity or motivation behind actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fixme
    -0.60
    WT
    -0.59
    but
    -0.59
     Travels
    -0.59
    osi
    -0.58
    folios
    -0.56
    USD
    -0.56
     But
    -0.55
    schild
    -0.55
    orie
    -0.54
    POSITIVE LOGITS
     nonetheless
    1.48
    etheless
    1.15
     nevertheless
    1.10
     anyway
    0.73
     darn
    0.71
     outwe
    0.67
     awfully
    0.65
     anyways
    0.64
     stubborn
    0.60
     caution
    0.59
    Activations Density 1.603%

    No Known Activations