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. 7-RES-JB
    6. 3358
    Prev
    Next
    INDEX
    Explanations

    Twitter handles and related metadata in text data

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media accounts or handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATIVE
    -0.77
     CONTROL
    -0.76
    IZE
    -0.74
    INESS
    -0.74
     Gamble
    -0.73
    âĸ¬
    -0.71
    idates
    -0.70
     LIFE
    -0.70
    ingham
    -0.68
     Bunny
    -0.68
    POSITIVE LOGITS
    cd
    1.02
    cs
    1.00
    fp
    0.93
    cc
    0.92
    ucl
    0.92
    isoft
    0.91
    nm
    0.91
    ickets
    0.90
    gs
    0.90
    pd
    0.89
    Activations Density 0.117%

    No Known Activations