© 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. 3-RES-JB
    11. 12787
    Prev
    Next
    INDEX
    Explanations

    the word "Finally" at the end of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Finally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ozo
    -0.77
    sic
    -0.66
    pattern
    -0.62
    hist
    -0.61
    induced
    -0.61
    nom
    -0.60
    eding
    -0.60
    dist
    -0.59
    hari
    -0.58
    policy
    -0.58
    POSITIVE LOGITS
     reunited
    0.83
    icia
    0.77
     Shutdown
    0.73
     Finished
    0.72
     reun
    0.69
     restart
    0.68
     Thumbnails
    0.67
     reunion
    0.66
    elvet
    0.65
     exha
    0.63
    Activations Density 0.012%

    No Known Activations