© 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. 4386
    Prev
    Next
    INDEX
    Explanations

    contemplative statements or situations

    oai_token-act-pair · gpt-3.5-turbo

    sentences that present lists or multiple points

    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
    urated
    -0.68
    daq
    -0.66
     nas
    -0.58
    wick
    -0.57
     proud
    -0.57
    urch
    -0.56
     trailing
    -0.55
    ebook
    -0.55
    rael
    -0.54
     MS
    -0.54
    POSITIVE LOGITS
     Firstly
    1.56
    Firstly
    1.34
     namely
    1.13
     Specifically
    0.89
    âĹı
    0.86
    Reviewer
    0.83
     First
    0.81
     viz
    0.79
    :-
    0.76
    First
    0.76
    Activations Density 0.323%

    No Known Activations