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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23189
    Prev
    Next
    INDEX
    Explanations

    financial and business-related terms and metaphors

    oai_token-act-pair · gpt-3.5-turbo

    metaphors and idiomatic expressions related to caution and awareness

    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
     proficiency
    -0.66
     Highlights
    -0.64
    rongh
    -0.63
     Minor
    -0.60
    ths
    -0.58
    itu
    -0.58
     ancestor
    -0.57
     proficient
    -0.57
     Frequ
    -0.56
    street
    -0.56
    POSITIVE LOGITS
     comprom
    0.88
    quickShipAvailable
    0.78
    erity
    0.75
     gloves
    0.71
     intervened
    0.67
    ippery
    0.65
     ticking
    0.64
     prevailed
    0.61
     conclud
    0.61
     proverbial
    0.61
    Activations Density 0.724%

    No Known Activations