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. 1-RES-JB
    6. 17225
    Prev
    Next
    INDEX
    Explanations

    the specific term "LE" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "LE" followed by a number, typically referring to a software or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.94
    Downloadha
    -0.90
    aneers
    -0.84
    ãĤ±
    -0.84
    ãĤ¹ãĥĪ
    -0.82
    uitous
    -0.80
    etheless
    -0.79
    ifice
    -0.78
    ãĥ¼ãĥĨ
    -0.76
    gerald
    -0.76
    POSITIVE LOGITS
     LE
    1.20
    ATHER
    1.03
    IGH
    0.94
    FT
    0.89
    LE
    0.89
    lean
    0.88
    ather
    0.85
    ASE
    0.83
    FS
    0.82
    ASON
    0.82
    Activations Density 0.003%

    No Known Activations