© 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. 1-RES-JB
    11. 24020
    Prev
    Next
    INDEX
    Explanations

    words or word fragments containing "ern"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ern" within various contexts

    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
    EStreamFrame
    -0.72
    late
    -0.68
    tin
    -0.67
     collagen
    -0.65
     Moderate
    -0.63
     moderate
    -0.63
     CPC
    -0.62
     trickle
    -0.61
     marrow
    -0.60
    KING
    -0.60
    POSITIVE LOGITS
    ern
    1.26
    opol
    1.06
    icter
    1.03
    ophon
    1.02
    acle
    1.00
    ophe
    0.98
    ocent
    0.93
    acular
    0.92
    esse
    0.91
    sburg
    0.91
    Activations Density 0.008%

    No Known Activations