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. 4190
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical and statistical concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to Bayesian statistics and probability distributions

    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
     whistlebl
    -0.87
    ][/
    -0.74
     perks
    -0.72
     hostilities
    -0.70
     Kens
    -0.69
     stamina
    -0.69
     adrenaline
    -0.68
     enthusi
    -0.68
     dads
    -0.68
     adren
    -0.68
    POSITIVE LOGITS
     theorem
    1.27
     algebra
    1.11
     \(\
    1.09
     $\
    1.07
     \(
    1.04
    orem
    1.03
     coefficients
    1.00
    gebra
    0.98
    ensional
    0.98
     Mathemat
    0.96
    Activations Density 0.406%

    No Known Activations