© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6608
    Prev
    Next
    INDEX
    Explanations

    references to the search engine "Bing"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the search engine Bing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -1.08
    kell
    -0.66
    ials
    -0.65
    intage
    -0.62
    aunder
    -0.60
     TODAY
    -0.60
    pires
    -0.59
    izer
    -0.59
    ãĤ·ãĥ£
    -0.58
     covari
    -0.56
    POSITIVE LOGITS
     Crosby
    0.95
    tons
    0.92
    ham
    0.87
    o
    0.83
    wich
    0.79
    olean
    0.78
    enstein
    0.76
    oing
    0.74
    xy
    0.73
    bats
    0.71
    Activations Density 0.067%

    No Known Activations