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. 9-RES-JB
    6. 21437
    Prev
    Next
    INDEX
    Explanations

    terms related to technological advancements and improvements, particularly focusing on efficiency, energy consumption, and battery life

    oai_token-act-pair · gpt-3.5-turbo

    terms related to performance and efficiency improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶŁ
    -0.72
    prep
    -0.72
    ãĤ¢ãĥ«
    -0.71
    ç«
    -0.70
    sel
    -0.70
    ãĤ³
    -0.69
    ãĥĥãĥĪ
    -0.64
    LAB
    -0.64
    ãĥĬ
    -0.64
    ISC
    -0.63
    POSITIVE LOGITS
     compared
    0.85
     coupled
    0.79
     (<
    0.75
     due
    0.72
     (~
    0.70
     Daredevil
    0.70
     amongst
    0.67
    ã
    0.66
     (>
    0.66
     unmatched
    0.65
    Activations Density 0.390%

    No Known Activations