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. 15493
    Prev
    Next
    INDEX
    Explanations

    words related to business incubators and facilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to business incubators and their functions

    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
    BOOK
    -0.70
    historic
    -0.68
     Honour
    -0.65
     unsupported
    -0.64
    HY
    -0.64
     pity
    -0.62
     Pension
    -0.61
     Crimean
    -0.60
    fight
    -0.59
     WWII
    -0.59
    POSITIVE LOGITS
     incub
    1.72
    uates
    0.91
    rador
    0.88
    icol
    0.84
     destro
    0.81
    iously
    0.80
    ators
    0.79
    ator
    0.75
    uggets
    0.73
    vier
    0.72
    Activations Density 0.007%

    No Known Activations