© 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. 2228
    Prev
    Next
    INDEX
    Explanations

    definite articles 'the'

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating problems or issues

    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
    otte
    -0.80
    ividual
    -0.76
    artifacts
    -0.75
    rils
    -0.74
    forms
    -0.74
    sites
    -0.73
    apons
    -0.71
    ovich
    -0.70
    ucl
    -0.70
    rand
    -0.69
    POSITIVE LOGITS
     gist
    1.48
     dilemma
    1.14
     extent
    1.12
     essence
    1.11
     point
    1.10
     takeaway
    1.10
     lesson
    1.10
     beauty
    1.08
     reason
    1.07
     premise
    1.06
    Activations Density 0.080%

    No Known Activations