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. 18183
    Prev
    Next
    INDEX
    Explanations

    programming code syntax

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "@" symbol, which is often used in online communication and social media contexts

    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
     Leth
    -0.73
     Gillespie
    -0.72
     Ballistic
    -0.71
     Baltic
    -0.69
     Ballard
    -0.68
     Mald
    -0.67
     Morales
    -0.66
     Lauder
    -0.66
     circulation
    -0.65
     Vie
    -0.64
    POSITIVE LOGITS
    #$
    1.18
    @@@@@@@@
    1.06
    gmail
    1.01
    wcsstore
    0.93
    home
    0.92
    echo
    0.87
    Home
    0.86
    realDonaldTrump
    0.82
    import
    0.82
    example
    0.81
    Activations Density 0.017%

    No Known Activations