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. 10-RES-JB
    6. 20912
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific terms that are phonetically related

    oai_token-act-pair · gpt-3.5-turbo

    words related to pronunciation and language structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Minimum
    -0.86
     Industrial
    -0.74
     Changing
    -0.69
     Current
    -0.67
     Establishment
    -0.67
     Struct
    -0.67
     settings
    -0.67
     longstanding
    -0.66
     Elastic
    -0.66
     Increasing
    -0.66
    POSITIVE LOGITS
    É
    1.39
    ËĪ
    1.31
    Äĵ
    1.05
    tu
    1.05
    toe
    1.04
    qq
    1.03
    JV
    1.02
    sein
    1.02
    β
    1.02
    raq
    1.01
    Activations Density 0.147%

    No Known Activations