© 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. 10-RES-JB
    11. 10617
    Prev
    Next
    INDEX
    Explanations

    words denoting causation or attribution

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or reasons

    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
    anka
    -0.60
     Chains
    -0.58
     clipboard
    -0.57
    stars
    -0.57
    hold
    -0.56
     STATES
    -0.53
     snipp
    -0.52
     Carbuncle
    -0.52
    ahs
    -0.52
    orum
    -0.52
    POSITIVE LOGITS
     partly
    1.33
     chiefly
    1.22
     principally
    1.16
     largely
    1.16
     mainly
    1.13
     primarily
    1.11
     partially
    1.03
     mostly
    0.98
     solely
    0.96
     entirely
    0.92
    Activations Density 0.144%

    No Known Activations