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. 10-RES-JB
    6. 20649
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions and determine their relations and structures (e.g., 'of', 'on', 'and')

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate rankings or degrees of comparison

    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
    tera
    -0.96
    krit
    -0.81
    hyde
    -0.81
    kamp
    -0.78
    Ô
    -0.73
    gow
    -0.73
    miah
    -0.72
    riber
    -0.70
    ql
    -0.70
    culosis
    -0.69
    POSITIVE LOGITS
     evils
    0.85
     times
    0.81
     earners
    0.80
     intentions
    0.79
     highs
    0.79
     pursuits
    0.78
     lows
    0.76
     equals
    0.76
     all
    0.75
     them
    0.75
    Activations Density 0.069%

    No Known Activations