© 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. 11-RES-JB
    11. 22343
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases indicating similarity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    expressions and phrases that indicate repetition or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    front
    -0.75
    dash
    -0.72
    ãĥĥ
    -0.71
    rend
    -0.70
    their
    -0.70
     Helpful
    -0.68
    rection
    -0.68
    ENDED
    -0.68
    replace
    -0.68
    orse
    -0.67
    POSITIVE LOGITS
     applies
    1.33
     goes
    1.22
     thing
    1.15
     happens
    1.07
     holds
    1.01
     principle
    0.99
     cannot
    0.99
     principles
    0.97
     happened
    0.96
     fate
    0.93
    Activations Density 0.043%

    No Known Activations