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. 11-RES-JB
    6. 10336
    Prev
    Next
    INDEX
    Explanations

    alphanumeric strings mixed with colloquial text, which seem to be related to technology or industry-specific jargon

    oai_token-act-pair · gpt-3.5-turbo

    references to wind energy technology and its applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kro
    -0.81
    lesh
    -0.81
    meat
    -0.80
     Kab
    -0.80
     kidney
    -0.80
    ylum
    -0.80
    Meat
    -0.79
     Burger
    -0.79
    interstitial
    -0.78
    urger
    -0.78
    POSITIVE LOGITS
    Wind
    2.09
     Wind
    2.06
     wind
    2.06
     Winds
    1.77
    wind
    1.74
     winds
    1.64
     Weather
    1.63
     storms
    1.59
    Weather
    1.55
     turbines
    1.52
    Activations Density 0.290%

    No Known Activations