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. 10-RES-JB
    6. 359
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the act of removal or elimination

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Rem" indicating a focus on updates or adaptations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REF
    -0.64
    realDonaldTrump
    -0.62
     modern
    -0.62
     climate
    -0.61
     Hath
    -0.59
    åŃ
    -0.58
     McCabe
    -0.58
     summar
    -0.58
     reader
    -0.57
     Typh
    -0.57
    POSITIVE LOGITS
    arkable
    1.44
    oving
    1.38
    ovable
    1.36
    nants
    1.33
    aining
    1.32
    arks
    1.24
    ittance
    1.20
    oval
    1.16
    ainers
    1.14
    oves
    1.14
    Activations Density 0.015%

    No Known Activations