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. 6688
    Prev
    Next
    INDEX
    Explanations

    terms related to the idea of utilizing or controlling something for a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    the term "harness" in various contexts, often referring to utilizing or employing some form of power or capability

    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
    ihad
    -0.70
     Empires
    -0.70
    estate
    -0.69
    onymous
    -0.65
    oslov
    -0.65
    deals
    -0.63
    cas
    -0.62
     Kubrick
    -0.62
    ochemical
    -0.60
    ographical
    -0.60
    POSITIVE LOGITS
     harness
    1.24
    pipe
    0.91
    atility
    0.91
    ions
    0.87
    ioned
    0.83
    ulic
    0.83
    es
    0.81
    ibly
    0.76
    icons
    0.75
    heny
    0.74
    Activations Density 0.006%

    No Known Activations