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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 17794
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics mentioned in reports and research findings

    oai_token-act-pair · gpt-3.5-turbo

    data and reports related to market trends and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivas
    -0.82
     exting
    -0.73
    arsity
    -0.72
    ²¾
    -0.70
    icably
    -0.69
    ctor
    -0.69
    Ĥ¬
    -0.66
    eeds
    -0.66
    iverpool
    -0.65
    issues
    -0.65
    POSITIVE LOGITS
     Statistics
    0.90
     OECD
    0.87
     Nielsen
    0.84
    manac
    0.82
     averages
    0.81
     comparison
    0.79
     Survey
    0.79
     Net
    0.77
     valuation
    0.77
     Wealth
    0.77
    Activations Density 0.197%

    No Known Activations