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. 10945
    Prev
    Next
    INDEX
    Explanations

    verbs related to rotational movement or change in direction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "flip" in various contexts

    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
     Lod
    -0.78
    ment
    -0.78
     Est
    -0.76
     Advocate
    -0.71
     Ces
    -0.70
    est
    -0.70
     Trib
    -0.70
    ella
    -0.69
    esse
    -0.68
     Mord
    -0.67
    POSITIVE LOGITS
     flip
    3.84
     flips
    2.54
     flipped
    2.44
     flipping
    2.34
     Flip
    2.25
     toss
    1.27
     upside
    1.22
     reverse
    1.22
     swing
    1.13
     tilt
    1.10
    Activations Density 0.015%

    No Known Activations