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. 7-RES-JB
    6. 18271
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing conjunctions and their connections in discussions of taxes and fiscal topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Shut
    -0.75
    LOCK
    -0.72
    lift
    -0.71
    las
    -0.66
    ied
    -0.65
    oward
    -0.65
    lit
    -0.64
    l
    -0.64
    Share
    -0.62
    Ĥİ
    -0.62
    POSITIVE LOGITS
     hence
    1.34
     consequently
    1.33
     therefore
    1.28
     thus
    1.28
     secondly
    1.16
     thereby
    1.12
     furthermore
    0.97
     moreover
    0.87
     consequ
    0.83
     vice
    0.83
    Activations Density 0.461%

    No Known Activations