© 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. 3501
    Prev
    Next
    INDEX
    Explanations

    verbs indicating causation or consequence

    oai_token-act-pair · gpt-3.5-turbo

    causal relationships and outcomes associated with various situations or conditions

    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
    inav
    -0.92
    Ha
    -0.67
     Marketable
    -0.64
    ighth
    -0.62
    ophen
    -0.61
     viz
    -0.61
    yt
    -0.61
    ha
    -0.60
     Tobacco
    -0.57
    nect
    -0.57
    POSITIVE LOGITS
     inex
    0.70
     resentment
    0.69
     many
    0.69
    wcs
    0.68
     Drag
    0.67
     investors
    0.66
     widespread
    0.66
     havoc
    0.62
     morale
    0.62
     goose
    0.62
    Activations Density 0.247%

    No Known Activations