Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 15793
    Prev
    Next
    INDEX
    Explanations

    names of professions or titles that end with 'teacher'

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "teacher."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sweep
    -0.62
    lessly
    -0.60
    ipolar
    -0.57
     filings
    -0.56
     vanish
    -0.56
    izons
    -0.55
     tsunami
    -0.55
     otherwise
    -0.55
    antha
    -0.55
     nowhere
    -0.55
    POSITIVE LOGITS
    llers
    1.45
    levision
    1.44
    achers
    1.44
    ller
    1.42
    acher
    1.38
    brates
    1.37
    aching
    1.35
    brate
    1.33
    achable
    1.25
    legraph
    1.16
    Activations Density 0.032%

    No Known Activations