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. 6-RES-JB
    6. 10269
    Prev
    Next
    INDEX
    Explanations

    mentions of the news organization NPR

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the NPR and PBS media organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mata
    -0.68
    gie
    -0.66
    oldemort
    -0.66
     Emirates
    -0.64
    cum
    -0.62
    wagen
    -0.62
     Templar
    -0.62
    gart
    -0.62
    loader
    -0.62
     ages
    -0.61
    POSITIVE LOGITS
    NPR
    1.14
     NPR
    1.02
    REC
    0.85
    DEF
    0.82
     transcripts
    0.80
     Radio
    0.79
    IB
    0.78
    TIT
    0.78
     Transcript
    0.78
    OST
    0.77
    Activations Density 0.009%

    No Known Activations