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. 7-RES-JB
    6. 10791
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases related to news agencies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "PA" typically related to press releases or news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lings
    -0.85
    tie
    -0.84
    worms
    -0.82
    naire
    -0.75
    worldly
    -0.71
    selves
    -0.67
    minded
    -0.66
    seeing
    -0.66
     measles
    -0.65
    worm
    -0.65
    POSITIVE LOGITS
    UL
    1.11
    WN
    1.08
    INT
    0.94
    BILITY
    0.89
    ignt
    0.89
    IRED
    0.88
    BLE
    0.87
    GE
    0.86
    USE
    0.85
    veyard
    0.81
    Activations Density 0.024%

    No Known Activations