© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 15894
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'a' at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    articles indicating the beginning of a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rir
    -0.75
     spiders
    -0.74
    jri
    -0.74
    Ħ¢
    -0.69
     cogn
    -0.67
    devices
    -0.67
     trending
    -0.66
    natureconservancy
    -0.65
     complying
    -0.63
     Hawks
    -0.63
    POSITIVE LOGITS
    ographer
    0.86
     assumes
    0.79
    OGR
    0.78
    ament
    0.76
    alian
    0.73
    etime
    0.68
    ographers
    0.68
    zes
    0.68
    asio
    0.67
    ography
    0.67
    Activations Density 0.000%

    No Known Activations