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. 3-RES-JB
    6. 21879
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the term "Horizon"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Horizon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anguage
    -1.07
    ographically
    -0.72
    conservancy
    -0.72
    女
    -0.70
    othing
    -0.69
    ogy
    -0.68
    tub
    -0.67
    upp
    -0.67
    oths
    -0.67
    RNA
    -0.66
    POSITIVE LOGITS
     Horizon
    1.12
     Collider
    0.96
    izons
    0.94
     Zero
    0.82
     Hole
    0.71
    vernment
    0.71
     Horizons
    0.70
    daq
    0.70
     Acceler
    0.69
     absor
    0.69
    Activations Density 0.009%

    No Known Activations