© 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. 13744
    Prev
    Next
    INDEX
    Explanations

    adjectives related to the quality of something

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs indicating actions or events

    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
    emption
    -0.60
    IE
    -0.55
    &
    -0.53
    ativity
    -0.52
     neighboring
    -0.51
    .*
    -0.51
     Warrant
    -0.50
    */
    -0.50
     pree
    -0.49
     ILCS
    -0.49
    POSITIVE LOGITS
     consisted
    0.77
     divided
    0.69
     varied
    0.67
     mainly
    0.66
     lasted
    0.63
     gradually
    0.63
    ktop
    0.63
     apologised
    0.63
     consist
    0.61
     travelled
    0.61
    Activations Density 0.378%

    No Known Activations