Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-RES-JB
    6. 10254
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Coyote" or its variations in text data

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Coy" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -1.04
    代
    -0.88
    é¾įå¥ij士
    -0.85
    uyomi
    -0.79
    */(
    -0.74
    ãĤ´ãĥ³
    -0.74
     ILCS
    -0.72
     certs
    -0.71
    à¥
    -0.70
    Reviewer
    -0.69
    POSITIVE LOGITS
    ote
    1.15
     Coy
    1.03
     coy
    0.92
    otes
    0.92
    stal
    0.90
    otle
    0.88
    aval
    0.82
    sters
    0.82
    cel
    0.80
     Coyotes
    0.77
    Activations Density 0.009%

    No Known Activations