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. 9-RES-JB
    6. 22164
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms related to physics, energy, and technology

    oai_token-act-pair · gpt-3.5-turbo

    sentences that describe processes or statements in a scientific or technical context

    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
    azel
    -0.73
    ascus
    -0.73
     enthusi
    -0.72
     deserved
    -0.70
     defiant
    -0.70
    intend
    -0.69
     welcome
    -0.68
    enged
    -0.68
    ŃĶ
    -0.68
     tack
    -0.67
    POSITIVE LOGITS
     Typically
    1.58
     Therefore
    1.47
     Usually
    1.46
     Often
    1.42
     Thus
    1.42
     Consequently
    1.42
     Normally
    1.41
     Depending
    1.38
     Hence
    1.37
     These
    1.35
    Activations Density 0.333%

    No Known Activations