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. 0-RES-JB
    6. 22863
    Prev
    Next
    INDEX
    Explanations

    terms related to low values or rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to low quantities or levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mirrors
    -0.67
     dinosaur
    -0.61
     chairs
    -0.61
     attest
    -0.60
     pieces
    -0.59
     seeds
    -0.58
     words
    -0.58
     ver
    -0.57
     giant
    -0.57
     arms
    -0.56
    POSITIVE LOGITS
    low
    4.30
    Low
    2.10
    high
    1.79
     LOW
    1.68
    lower
    1.64
     Low
    1.59
    highest
    1.37
     lows
    1.33
    worst
    1.33
     low
    1.29
    Activations Density 0.010%

    No Known Activations