Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9927
    Prev
    Next
    INDEX
    Explanations

    file types and programming language syntax

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and symbols, particularly those appearing at the end of sentences or other distinctive markers

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

    No Comments

    Negative Logits
    ailability
    -0.79
    ailable
    -0.76
    ĪĴ
    -0.71
    actionDate
    -0.68
     CBC
    -0.67
     pestic
    -0.66
    ensical
    -0.64
     occas
    -0.63
     inertia
    -0.62
     exception
    -0.62
    POSITIVE LOGITS
    agall
    0.88
    espie
    0.86
    ierrez
    0.83
    veland
    0.77
    ppe
    0.74
    raltar
    0.72
    uez
    0.70
    herer
    0.70
    heit
    0.70
    anamo
    0.70
    Activations Density 0.397%

    No Known Activations