© 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. 8-RES-JB
    11. 20468
    Prev
    Next
    INDEX
    Explanations

    actions related to physical movement, such as walking, driving, and swimming

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating connections or relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.67
    èĢħ
    -0.65
    oids
    -0.65
    atis
    -0.64
    invoke
    -0.63
     Majority
    -0.62
    va
    -0.62
    pps
    -0.61
     XY
    -0.61
     Coalition
    -0.60
    POSITIVE LOGITS
     photograp
    1.04
     repairing
    1.03
     shaping
    0.99
     finishing
    0.96
     uploading
    0.96
     moaning
    0.94
     biking
    0.94
     smelling
    0.94
     singing
    0.93
     grooming
    0.93
    Activations Density 0.262%

    No Known Activations