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. 6-RES-JB
    6. 23569
    Prev
    Next
    INDEX
    Explanations

    terms related to a "boost", particularly in relation to various contexts like technology, gaming, health, and finance

    oai_token-act-pair · gpt-3.5-turbo

    the term "boost" in various contexts and usages, indicating enhancement or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.77
    âĸ¬âĸ¬
    -0.73
    rors
    -0.72
    changes
    -0.71
    bryce
    -0.69
     WATCHED
    -0.67
    URES
    -0.67
    POL
    -0.66
    âĸ¬
    -0.66
    Maps
    -0.65
    POSITIVE LOGITS
     boost
    0.87
     boosting
    0.80
    itive
    0.75
    chairs
    0.73
    xual
    0.73
    hetamine
    0.72
    ollen
    0.72
    boost
    0.72
     morale
    0.71
     absor
    0.70
    Activations Density 0.022%

    No Known Activations