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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 7382
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Lamb"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Lamb" and variations of the word "lamb"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thumbnails
    -0.82
    asion
    -0.68
    Sense
    -0.67
     phil
    -0.65
    PIN
    -0.65
     prescription
    -0.64
     selfie
    -0.63
    pin
    -0.63
    asin
    -0.62
    genic
    -0.62
    POSITIVE LOGITS
     Lamb
    4.18
     lamb
    2.45
     lambda
    1.30
    lambda
    1.17
     Shepherd
    1.16
     Rabbit
    1.12
     Abel
    1.11
     Hamb
    1.10
     Lem
    1.06
     Lam
    1.05
    Activations Density 0.023%

    No Known Activations