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. 5-RES-JB
    6. 8505
    Prev
    Next
    INDEX
    Explanations

    acronyms consisting of two capital letters followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to specific codes or acronyms, particularly those that start with "EG."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.90
    itude
    -0.74
    ãĥĥãĤ¯
    -0.72
    ño
    -0.70
    achus
    -0.69
    tenance
    -0.69
    thren
    -0.67
    ched
    -0.65
    ãĥ¼ãĥ³
    -0.65
    itia
    -0.65
    POSITIVE LOGITS
    REG
    0.93
    BIT
    0.85
    LES
    0.80
    entric
    0.79
    ossip
    0.78
    ILE
    0.78
    ERG
    0.77
    LER
    0.77
    roups
    0.77
    IVERS
    0.76
    Activations Density 0.014%

    No Known Activations