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. 0-RES-JB
    6. 4291
    Prev
    Next
    INDEX
    Explanations

    words related to the behavior of auks

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the suffix "ks" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     judgment
    -0.63
     conviction
    -0.62
     simulator
    -0.61
    IRO
    -0.61
     relative
    -0.58
    worthiness
    -0.58
     judgement
    -0.58
     tolerated
    -0.56
    area
    -0.55
    æī
    -0.55
    POSITIVE LOGITS
    ks
    4.51
    KS
    2.16
    ksh
    2.05
    kson
    2.01
    ked
    2.00
    king
    1.87
    kish
    1.70
    cks
    1.58
    kt
    1.54
    kers
    1.52
    Activations Density 0.013%

    No Known Activations