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. 11041
    Prev
    Next
    INDEX
    Explanations

    the word "excel" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "cel" and related entities or names

    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
    ammy
    -0.85
    è¦ļéĨĴ
    -0.83
     Parables
    -0.75
    enegger
    -0.74
    Reviewer
    -0.74
    daq
    -0.73
    */(
    -0.72
    ELF
    -0.70
    æĸ¹
    -0.67
    mble
    -0.67
    POSITIVE LOGITS
    estial
    1.23
    agos
    0.94
    ution
    0.88
    cel
    0.88
    aneous
    0.88
    ocity
    0.85
    ente
    0.84
    iev
    0.81
    utive
    0.81
    ibr
    0.80
    Activations Density 0.007%

    No Known Activations