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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 17124
    Prev
    Next
    INDEX
    Explanations

    words related to informal language or specialized vocabulary

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases associated with slang and jargon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Democr
    -0.75
    igious
    -0.66
     Dalai
    -0.65
    isner
    -0.62
    Mich
    -0.62
    clud
    -0.61
    spons
    -0.59
    MENT
    -0.59
    pard
    -0.58
    aur
    -0.58
    POSITIVE LOGITS
     terminology
    1.14
     jargon
    1.06
     shorthand
    1.02
     slang
    0.97
    peak
    0.96
    isms
    0.90
     phrases
    0.87
     notation
    0.86
     abbre
    0.83
     vocabulary
    0.82
    Activations Density 0.012%

    No Known Activations