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. 4-RES-JB
    6. 17833
    Prev
    Next
    INDEX
    Explanations

    terms related to unintended secondary results or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "product."

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

    No Comments

    Negative Logits
    ITED
    -0.75
    CLASSIFIED
    -0.67
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.64
    ARP
    -0.63
     Shades
    -0.62
     NOTICE
    -0.62
     mosqu
    -0.61
    apo
    -0.60
     Tarant
    -0.60
     [|
    -0.60
    POSITIVE LOGITS
    ivity
    1.18
    ively
    1.15
    iveness
    1.03
    ivities
    0.98
    ions
    0.87
    arian
    0.79
    iation
    0.79
    Hunt
    0.76
    ivist
    0.76
    ogenous
    0.75
    Activations Density 0.019%

    No Known Activations