© 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. 22294
    Prev
    Next
    INDEX
    Explanations

    phrases containing descriptions or attributions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve descriptions or characterizations of people, events, or concepts

    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
    ettlement
    -0.61
    abiding
    -0.59
    Zone
    -0.59
    ipeg
    -0.57
    cise
    -0.56
    acion
    -0.54
     reproduce
    -0.53
    olar
    -0.53
     Lor
    -0.53
    tein
    -0.53
    POSITIVE LOGITS
     favorably
    0.90
     skept
    0.87
     unfairly
    0.86
     sarcast
    0.71
    okingly
    0.70
     by
    0.69
     errone
    0.69
     harshly
    0.68
     negatively
    0.66
    ologically
    0.66
    Activations Density 0.153%

    No Known Activations