© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6701
    Prev
    Next
    INDEX
    Explanations

    relationships and descriptions related to causality

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causation or reasons for circumstances

    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
    agues
    -0.94
    cember
    -0.78
    orthy
    -0.76
    endar
    -0.75
    soon
    -0.74
    iak
    -0.74
    jah
    -0.73
    aughter
    -0.72
    és
    -0.72
    busters
    -0.72
    POSITIVE LOGITS
     lack
    1.20
     inherent
    1.11
     differences
    1.08
     limitations
    1.05
     inexper
    1.04
     lacking
    1.02
     cumbers
    1.01
     redundancy
    1.00
     inacc
    1.00
     proximity
    1.00
    Activations Density 0.186%

    No Known Activations