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. 5829
    Prev
    Next
    INDEX
    Explanations

    references to the Awami Tehreek political party or related topics

    oai_token-act-pair · gpt-3.5-turbo

    the term "Aw" in various contexts suggesting emphasis or disappointment

    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
     Gemini
    -0.75
     Hitler
    -0.75
     Kubrick
    -0.73
     Scientology
    -0.67
     Nazi
    -0.66
    Hyper
    -0.66
     Luthor
    -0.64
     Roosevelt
    -0.62
     Jenner
    -0.61
     flares
    -0.60
    POSITIVE LOGITS
    akening
    1.30
    ashington
    1.14
    akens
    1.11
    Aw
    1.11
     Aw
    1.09
    kward
    1.01
    adesh
    1.01
    atche
    0.99
    aii
    0.95
    ahoo
    0.95
    Activations Density 0.006%

    No Known Activations