© 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. 6153
    Prev
    Next
    INDEX
    Explanations

    phrases related to making comparisons or expressing opinions in a forceful manner

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "when it comes to" and variations on that structure

    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
    scribe
    -0.71
    noticed
    -0.60
    SAY
    -0.57
    WHO
    -0.57
    warning
    -0.57
     Sirius
    -0.57
    amen
    -0.56
     Morse
    -0.56
    aya
    -0.55
    KNOWN
    -0.54
    POSITIVE LOGITS
     comes
    1.20
     mattered
    1.07
     rains
    1.05
     Comes
    0.98
     matters
    0.92
     happens
    0.91
     occurs
    0.84
     boils
    0.82
     arises
    0.81
     arrives
    0.79
    Activations Density 0.065%

    No Known Activations