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. 7244
    Prev
    Next
    INDEX
    Explanations

    double characters separated by special characters

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers and symbols

    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
    nesday
    -0.92
     destro
    -0.88
     redes
    -0.74
     undermin
    -0.74
     dismantle
    -0.71
     consecut
    -0.69
     occas
    -0.69
    ury
    -0.69
     herself
    -0.68
     themselves
    -0.68
    POSITIVE LOGITS
     largeDownload
    1.00
    ccording
    0.95
    ³³³
    0.87
    Unless
    0.85
    ³³³³³³³³
    0.85
    ³³³³
    0.83
    ================================================================
    0.81
    âĿ
    0.80
    ³³³³³³³³³³³³³³³³
    0.80
    Okay
    0.78
    Activations Density 0.240%

    No Known Activations