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. 3-RES-JB
    6. 6816
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "FT"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the abbreviation "FT" associated with numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.79
    amus
    -0.75
    utical
    -0.72
    ãĥ¡
    -0.72
    utive
    -0.71
     è£ıç
    -0.71
    Gas
    -0.70
     Tosh
    -0.69
     CVE
    -0.68
     Camb
    -0.67
    POSITIVE LOGITS
    raction
    0.95
    reet
    0.90
    riter
    0.88
    ritz
    0.85
    WD
    0.83
    auld
    0.83
    RA
    0.82
    itle
    0.81
    rees
    0.81
    hend
    0.80
    Activations Density 0.009%

    No Known Activations