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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12020
    Prev
    Next
    INDEX
    Explanations

    usernames or aliases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to usernames and aliases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewed
    -0.71
    aud
    -0.69
    urb
    -0.68
    oons
    -0.67
    icult
    -0.67
    itsch
    -0.67
    OTT
    -0.67
    aith
    -0.66
    akh
    -0.64
    yrinth
    -0.64
    POSITIVE LOGITS
     username
    0.94
     Username
    0.92
     aliases
    0.88
    username
    0.87
     alias
    0.85
     belonging
    0.81
     persona
    0.79
     Generator
    0.78
    ccess
    0.73
     surname
    0.73
    Activations Density 0.044%

    No Known Activations