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. 1-RES-JB
    6. 18287
    Prev
    Next
    INDEX
    Explanations

    instances where actions are done or considered individually or separately

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "separately."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.78
    enos
    -0.74
    IENCE
    -0.66
    wy
    -0.65
    yo
    -0.65
    eno
    -0.62
    odan
    -0.62
    ger
    -0.62
    LD
    -0.62
     Kelvin
    -0.62
    POSITIVE LOGITS
     separately
    1.00
     detach
    0.84
     guiActiveUn
    0.83
    ilitary
    0.80
     ported
    0.75
    psey
    0.74
     sexes
    0.73
     boxed
    0.71
     tang
    0.70
    comings
    0.70
    Activations Density 0.002%

    No Known Activations