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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 11
    Prev
    Next
    INDEX
    Explanations

    phrases related to angular concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Ang," "Angular," and "Angry."

    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
     crypt
    -0.77
     FedEx
    -0.73
     Waters
    -0.71
     cheese
    -0.71
     supplemental
    -0.71
     Zot
    -0.71
    ttes
    -0.69
     password
    -0.68
     caps
    -0.67
    tsky
    -0.67
    POSITIVE LOGITS
    Ang
    3.89
     Angular
    1.93
     Ang
    1.85
    angular
    1.65
     ANG
    1.58
     Angry
    1.57
     Angle
    1.44
     ang
    1.44
     angular
    1.43
    ang
    1.27
    Activations Density 0.015%

    No Known Activations