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. 6-RES-JB
    6. 6525
    Prev
    Next
    INDEX
    Explanations

    proper nouns such as names of military generals

    oai_token-act-pair · gpt-3.5-turbo

    references to high-ranking military officials and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ailability
    -0.84
    SourceFile
    -0.78
    ĵĺ
    -0.78
    ategory
    -0.76
    liga
    -0.76
    Downloadha
    -0.75
    unal
    -0.74
    comings
    -0.68
    comed
    -0.67
    ĸļ
    -0.67
    POSITIVE LOGITS
     Doomsday
    0.76
    alogy
    0.70
     Atkins
    0.67
    uez
    0.67
    ciating
    0.66
    clear
    0.65
    Knight
    0.65
    iani
    0.64
     guiActiveUnfocused
    0.64
     Tenth
    0.63
    Activations Density 0.104%

    No Known Activations