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. 0-RES-JB
    6. 5706
    Prev
    Next
    INDEX
    Explanations

    numbers and scientific or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.77
    ecause
    -0.65
     ItemLevel
    -0.64
    onga
    -0.60
    ogun
    -0.60
    him
    -0.59
    wark
    -0.59
    olean
    -0.59
    iard
    -0.53
    ruary
    -0.53
    POSITIVE LOGITS
     antioxid
    0.89
    natureconservancy
    0.79
     tradem
    0.79
     millenn
    0.79
     Seym
    0.78
    Balt
    0.77
    ß
    0.75
    kefeller
    0.73
    PDATE
    0.72
    GoldMagikarp
    0.72
    Activations Density 7.788%

    No Known Activations