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. 22821
    Prev
    Next
    INDEX
    Explanations

    references to the British Broadcasting Corporation (BBC)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the BBC

    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
    pell
    -0.87
    hammad
    -0.79
    holders
    -0.77
    mble
    -0.76
    cles
    -0.74
    istries
    -0.72
    plet
    -0.72
    utics
    -0.72
    gew
    -0.70
    ients
    -0.70
    POSITIVE LOGITS
    ODE
    0.91
    ode
    0.90
     Tycoon
    0.89
     Broadcasting
    0.86
     Radio
    0.81
    OST
    0.81
    IJ
    0.80
     News
    0.78
     Monitoring
    0.78
     Mub
    0.77
    Activations Density 0.020%

    No Known Activations