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. 3-RES-JB
    6. 10442
    Prev
    Next
    INDEX
    Explanations

    words related to reaching new heights or levels of excellence

    oai_token-act-pair · gpt-3.5-turbo

    words related to rising or elevation concepts

    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
    mith
    -0.69
    OH
    -0.67
    ãĥ£
    -0.66
    beit
    -0.66
     subp
    -0.63
    ãĥĻ
    -0.62
     brow
    -0.61
    olan
    -0.60
    ãĤ§
    -0.60
     Bought
    -0.60
    POSITIVE LOGITS
    ental
    1.27
    ence
    1.25
    ential
    1.23
    ancy
    1.12
    entially
    1.10
    ences
    1.07
    ent
    0.99
    encia
    0.98
    ently
    0.98
    ente
    0.97
    Activations Density 0.013%

    No Known Activations