© 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. 6-RES-JB
    11. 20595
    Prev
    Next
    INDEX
    Explanations

    actions involving effort or determination

    oai_token-act-pair · gpt-3.5-turbo

    activities involving effort or struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ca
    -0.73
     locality
    -0.70
     grouping
    -0.69
    henko
    -0.68
    Ger
    -0.66
    cens
    -0.66
    ensable
    -0.65
    eka
    -0.64
    nl
    -0.62
    redo
    -0.61
    POSITIVE LOGITS
    BIL
    0.68
     rodents
    0.66
     rodent
    0.66
     Mouse
    0.65
     furiously
    0.65
    antry
    0.65
     mice
    0.63
     adolesc
    0.62
     rats
    0.61
    regor
    0.61
    Activations Density 0.185%

    No Known Activations