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. 7-RES-JB
    6. 15658
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Lamb"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Lamb" or variations of the word in the text

    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
    PLIED
    -0.81
    BOOK
    -0.75
    ãĥ¯
    -0.73
     Kindle
    -0.68
     Occupations
    -0.65
    Downloadha
    -0.64
    ãģ¦
    -0.64
    LIST
    -0.64
    AMI
    -0.64
     drift
    -0.62
    POSITIVE LOGITS
    da
    0.98
    asted
    0.94
    inate
    0.92
    rett
    0.90
    alle
    0.89
    osal
    0.89
    ofi
    0.88
    onde
    0.87
    din
    0.86
    alo
    0.85
    Activations Density 0.030%

    No Known Activations