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. 6-RES-JB
    6. 6346
    Prev
    Next
    INDEX
    Explanations

    comparative phrases emphasizing superiority or importance

    oai_token-act-pair · gpt-3.5-turbo

    comparisons indicating that something exceeds or surpasses another in some way

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAW
    -0.65
     Nanto
    -0.65
    OSE
    -0.64
     largeDownload
    -0.64
    CLASSIFIED
    -0.64
    NEY
    -0.62
    ãĥ¡
    -0.59
    ãĤ´ãĥ³
    -0.59
    DH
    -0.59
    culosis
    -0.57
    POSITIVE LOGITS
    whelming
    0.84
    usercontent
    0.73
    atos
    0.72
     tripled
    0.70
    represent
    0.67
    represented
    0.67
    lyak
    0.66
     doubling
    0.66
     doubled
    0.63
    integer
    0.61
    Activations Density 0.061%

    No Known Activations