© 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. 11146
    Prev
    Next
    INDEX
    Explanations

    phrases related to exerting control over others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" and its variations to assess purpose or intention

    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
    rolled
    -0.71
     Shot
    -0.69
    rar
    -0.68
     Wanted
    -0.65
     Recorded
    -0.64
     Known
    -0.63
     rolled
    -0.62
    rum
    -0.62
     largeDownload
    -0.60
    pict
    -0.59
    POSITIVE LOGITS
     maximize
    1.13
     achieve
    1.05
     compensate
    1.05
     justify
    1.05
    adies
    1.01
     ensure
    1.01
     minimize
    1.01
     accommodate
    1.00
    wered
    1.00
     varying
    0.98
    Activations Density 0.176%

    No Known Activations