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. 19058
    Prev
    Next
    INDEX
    Explanations

    Economic and financial terms such as brand names or related phrases

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to media and organizations

    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
    iasis
    -0.73
     istg
    -0.72
    tenance
    -0.72
    ãĥ´ãĤ¡
    -0.70
    ured
    -0.70
    Scotland
    -0.70
    ................................................................
    -0.69
    henko
    -0.68
    osaurus
    -0.66
    idates
    -0.65
    POSITIVE LOGITS
    FP
    0.93
    HL
    0.89
    FU
    0.88
    nesday
    0.86
    ITH
    0.85
    RAFT
    0.83
    TING
    0.83
    TW
    0.82
    ITNESS
    0.82
    DF
    0.81
    Activations Density 0.010%

    No Known Activations