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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 12804
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to programming or software development

    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
    Cele
    -0.69
    drug
    -0.69
    north
    -0.65
    deen
    -0.63
    osterone
    -0.62
     Gulf
    -0.61
    SPONSORED
    -0.60
     Roz
    -0.60
    Northern
    -0.60
    south
    -0.59
    POSITIVE LOGITS
     recursive
    1.02
     deprecated
    0.97
     JSON
    0.96
     GUI
    0.95
     Python
    0.93
     plugin
    0.93
     debugging
    0.93
     initialization
    0.93
     configure
    0.92
     runtime
    0.92
    Activations Density 1.578%

    No Known Activations