© 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. 3-RES-JB
    11. 21231
    Prev
    Next
    INDEX
    Explanations

    words that indicate causation or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causality or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.74
    afort
    -0.68
    eatures
    -0.65
    atoes
    -0.63
    pload
    -0.61
    rehens
    -0.61
    ategor
    -0.60
    ivas
    -0.59
    agan
    -0.59
    aves
    -0.59
    POSITIVE LOGITS
    better
    0.93
    gers
    0.85
    wcs
    0.84
    lead
    0.81
    ership
    0.71
    ãĥĥãĥī
    0.70
     leading
    0.68
     Leading
    0.68
    rid
    0.67
    ging
    0.67
    Activations Density 0.033%

    No Known Activations