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. 10-RES-JB
    6. 21110
    Prev
    Next
    INDEX
    Explanations

    terms related to diversification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to diversification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fax
    -0.81
    Reloaded
    -0.77
    Madison
    -0.70
     Archdemon
    -0.65
     Sheridan
    -0.61
    ³³³³³³³³³³³³³³³³
    -0.61
    ERA
    -0.61
    ATA
    -0.59
     Angela
    -0.58
     Centauri
    -0.57
    POSITIVE LOGITS
    ified
    1.42
    ification
    1.38
    ions
    1.30
    ifying
    1.30
    ify
    1.22
    ifies
    1.17
    ifiers
    1.17
    ities
    1.13
    iversity
    1.12
    ifier
    1.11
    Activations Density 0.023%

    No Known Activations