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. 16045
    Prev
    Next
    INDEX
    Explanations

    comparative phrases such as "as well as."

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases and expressions indicating similarity or equivalence

    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
    oller
    -0.80
    lez
    -0.80
    upt
    -0.73
    stall
    -0.71
    erest
    -0.68
    Rub
    -0.65
    ople
    -0.65
    ijah
    -0.63
    leg
    -0.63
    hal
    -0.62
    POSITIVE LOGITS
     evidenced
    1.29
     regards
    1.14
    piring
    1.10
    pects
    1.05
     opposed
    1.02
     well
    0.98
     soon
    0.98
    ylum
    0.88
    piration
    0.87
    pired
    0.87
    Activations Density 0.152%

    No Known Activations