© 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. 3-RES-JB
    11. 10655
    Prev
    Next
    INDEX
    Explanations

    words that contain the subsequence "ern"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ern," likely indicating a focus on specific names or terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.68
    xon
    -0.67
    KING
    -0.66
     collagen
    -0.64
     inhibitors
    -0.63
     trickle
    -0.63
    Arcade
    -0.62
     prominently
    -0.60
     resisting
    -0.60
    tin
    -0.59
    POSITIVE LOGITS
    opol
    1.11
    acle
    1.04
    atural
    0.91
    acles
    0.90
    icus
    0.89
    anke
    0.88
    ails
    0.88
    esse
    0.88
    ern
    0.87
    sburg
    0.86
    Activations Density 0.008%

    No Known Activations