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. 7-RES-JB
    6. 10471
    Prev
    Next
    INDEX
    Explanations

    references to the word "Sar"

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive mention of the term "Sar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curfew
    -0.70
     Lovecraft
    -0.69
     flourish
    -0.68
     habitable
    -0.63
    éĹĺ
    -0.62
    STER
    -0.60
     numbering
    -0.59
     sterling
    -0.59
     Dangerous
    -0.59
     developmental
    -0.59
    POSITIVE LOGITS
    kees
    1.32
    andon
    1.09
    ban
    1.07
    pling
    1.04
    wark
    1.02
    atos
    1.00
    ashtra
    0.99
    thal
    0.98
    vati
    0.98
    ussian
    0.96
    Activations Density 0.023%

    No Known Activations