© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 24016
    Prev
    Next
    INDEX
    Explanations

    references to things being officially announced or proclaimed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "declared" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rabbit
    -0.69
    nesota
    -0.69
    OTOS
    -0.67
     Ninth
    -0.62
    imeo
    -0.61
    INTER
    -0.61
    fur
    -0.61
     Cats
    -0.61
    devices
    -0.60
     captcha
    -0.60
    POSITIVE LOGITS
     declares
    0.90
     declare
    0.86
     declaring
    0.85
     declared
    0.84
    ignty
    0.79
     proclaiming
    0.76
     proclaim
    0.76
     declarations
    0.74
     proclaimed
    0.70
     bankruptcy
    0.70
    Activations Density 0.018%

    No Known Activations