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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 3349
    Prev
    Next
    INDEX
    Explanations

    text indicating high values or large amounts

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific special character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reflex
    -0.90
     favor
    -0.89
     synerg
    -0.87
     favour
    -0.85
     spir
    -0.81
     enriched
    -0.81
     accomp
    -0.77
     territorial
    -0.76
     domest
    -0.76
     pri
    -0.75
    POSITIVE LOGITS
    Because
    1.35
    It
    1.30
    What
    1.27
    There
    1.26
    One
    1.25
    If
    1.24
    When
    1.24
    ccording
    1.23
    Sometimes
    1.22
    Now
    1.21
    Activations Density 0.097%

    No Known Activations