© 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. 8-RES-JB
    11. 20478
    Prev
    Next
    INDEX
    Explanations

    positive feedback or comments relating to the quality of design or execution in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    excellent writing and production qualities in creative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ospons
    -0.79
    wives
    -0.76
    interstitial
    -0.72
    pard
    -0.67
    adan
    -0.67
    ulf
    -0.67
    bringing
    -0.67
    vernment
    -0.67
    iatus
    -0.65
    ends
    -0.65
    POSITIVE LOGITS
     unchanged
    1.16
     interchangeable
    0.95
     impecc
    0.89
     varied
    0.89
     atro
    0.86
     intact
    0.83
     noticeably
    0.82
     untouched
    0.81
     flawless
    0.81
     fluid
    0.81
    Activations Density 0.537%

    No Known Activations