© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 19049
    Prev
    Next
    INDEX
    Explanations

    words related to lists or sequential information

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific repeated characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diminishing
    -0.67
     chunks
    -0.66
     ignition
    -0.65
     fading
    -0.65
     suicide
    -0.65
     scattering
    -0.64
     hydrogen
    -0.62
     slowing
    -0.61
     Mayer
    -0.60
     literacy
    -0.60
    POSITIVE LOGITS
    agree
    1.08
    mand
    1.05
    ï¸ı
    1.04
    have
    1.02
    need
    0.99
    want
    0.97
    know
    0.97
    require
    0.96
    intend
    0.95
    alm
    0.94
    Activations Density 0.123%

    No Known Activations