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

    Neuronpedia

    Jacobian LensNEW
    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. 18277
    Prev
    Next
    INDEX
    Explanations

    phrases indicating perseverance or determination

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "no matter" in various contexts

    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
    oute
    -0.81
    olis
    -0.68
    uctions
    -0.64
    zu
    -0.64
    Assembly
    -0.64
    ICT
    -0.63
    rian
    -0.63
    UES
    -0.62
    anto
    -0.62
    BSD
    -0.61
    POSITIVE LOGITS
     how
    1.17
     whatsoever
    1.01
     whether
    0.98
     HOW
    0.95
    how
    0.95
    whether
    0.86
     WHAT
    0.85
     what
    0.80
     whatever
    0.76
    etheless
    0.73
    Activations Density 0.019%

    No Known Activations