© 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. 10-RES-JB
    11. 16622
    Prev
    Next
    INDEX
    Explanations

    phrases indicating cause and effect

    oai_token-act-pair · gpt-3.5-turbo

    connecting words that indicate causation or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quit
    -0.77
    RAW
    -0.68
    ctions
    -0.65
     Swim
    -0.65
    wait
    -0.64
    wl
    -0.64
    rete
    -0.63
    cit
    -0.63
     boarded
    -0.63
    Submit
    -0.63
    POSITIVE LOGITS
     preventing
    1.66
     reducing
    1.66
     enabling
    1.59
     facilitating
    1.55
     allowing
    1.55
     enhancing
    1.54
     ensuring
    1.53
     eliminating
    1.50
     boosting
    1.49
     preserving
    1.48
    Activations Density 0.255%

    No Known Activations