© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 8382
    Prev
    Next
    INDEX
    Explanations

    mentions of the web browser "Edge"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Edge browser and its features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externalToEVAOnly
    -0.82
    undai
    -0.81
    umbling
    -0.81
    urally
    -0.81
    unal
    -0.79
    umbled
    -0.74
    aternal
    -0.72
    %]
    -0.72
    sburgh
    -0.71
    atem
    -0.70
    POSITIVE LOGITS
     Edge
    1.27
    Edge
    1.17
     Catalyst
    1.17
    combe
    0.94
     Grid
    0.83
    ners
    0.78
     Worlds
    0.77
     Islands
    0.76
    llan
    0.75
     Frontier
    0.74
    Activations Density 0.009%

    No Known Activations