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. 9087
    Prev
    Next
    INDEX
    Explanations

    the term "rogue" or related concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rogue" and terms associated with it

    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
     Butterfly
    -0.81
     Prem
    -0.77
     belts
    -0.76
     Belt
    -0.72
     Mant
    -0.71
    SHIP
    -0.71
    cms
    -0.70
     Bath
    -0.70
     mast
    -0.69
    atal
    -0.69
    POSITIVE LOGITS
     rogue
    1.51
    otle
    1.40
     unre
    1.35
    ARP
    1.30
     Rogue
    1.22
    Rogue
    1.13
     rog
    1.08
    amber
    1.06
    itton
    1.02
    IGN
    0.98
    Activations Density 0.050%

    No Known Activations