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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 23869
    Prev
    Next
    INDEX
    Explanations

    the word "back"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "go back"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.59
     Consent
    -0.57
     Newly
    -0.57
    uracy
    -0.57
    aspx
    -0.56
    %);
    -0.55
    %"
    -0.54
     Potential
    -0.54
     understatement
    -0.54
    Specifically
    -0.54
    POSITIVE LOGITS
    packing
    0.98
    door
    0.97
    dated
    0.94
    packs
    0.94
    stab
    0.93
    tracking
    0.92
    doors
    0.89
    wards
    0.88
    stairs
    0.86
    home
    0.85
    Activations Density 0.021%

    No Known Activations