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. 4-RES-JB
    6. 3578
    Prev
    Next
    INDEX
    Explanations

    related to theoretical concepts and calculations

    oai_token-act-pair · gpt-3.5-turbo

    references to theoretical concepts and models

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

    No Comments

    Negative Logits
    upon
    -0.76
     Furious
    -0.72
    win
    -0.71
    worthy
    -0.69
    orge
    -0.66
    xes
    -0.66
     Cele
    -0.64
    bows
    -0.64
    words
    -0.64
    rings
    -0.63
    POSITIVE LOGITS
     physicist
    0.96
     physicists
    0.88
    ity
    0.79
     theoretical
    0.75
    istically
    0.75
     feasibility
    0.74
    arial
    0.73
    ities
    0.73
    ité
    0.72
     equival
    0.71
    Activations Density 0.015%

    No Known Activations