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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20811
    Prev
    Next
    INDEX
    Explanations

    names and terms related to a specific person named McClure

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals, specifically those related to Steven McCluskey and other associated figures

    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
    Interstitial
    -0.88
     Gemini
    -0.85
    Reviewer
    -0.76
    Magikarp
    -0.72
    âĹ¼
    -0.72
    âĸ¬âĸ¬
    -0.69
    Ground
    -0.66
    FORE
    -0.66
     Bubble
    -0.64
     Barrier
    -0.63
    POSITIVE LOGITS
    atch
    0.91
    endon
    0.90
     McCl
    0.89
    ernand
    0.86
    atche
    0.86
    ivery
    0.82
    esi
    0.81
    ython
    0.81
    acks
    0.81
    uties
    0.80
    Activations Density 0.015%

    No Known Activations