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. 8-RES-JB
    6. 18961
    Prev
    Next
    INDEX
    Explanations

    words related to a specific context or brand, such as "Arc System Works" and "arcades"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Arc" or related concepts within a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.95
    tons
    -0.89
    ging
    -0.76
    bags
    -0.68
    cream
    -0.67
    fulness
    -0.66
    borgh
    -0.66
    tk
    -0.66
    glers
    -0.65
    gence
    -0.65
    POSITIVE LOGITS
    adia
    1.30
    adian
    1.13
    adium
    0.98
    uate
    0.96
    ades
    0.95
    illary
    0.89
    agraph
    0.86
    inia
    0.84
     Warden
    0.79
    Arc
    0.79
    Activations Density 0.074%

    No Known Activations