© 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. 22308
    Prev
    Next
    INDEX
    Explanations

    words related to strength and resilience

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'u'

    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
     Horizons
    -0.62
     Ceres
    -0.61
     Dahl
    -0.59
     Goth
    -0.59
     Associates
    -0.59
     Launch
    -0.59
     Zot
    -0.58
     Landing
    -0.57
     Collider
    -0.57
     Ahead
    -0.57
    POSITIVE LOGITS
    pered
    0.99
    vered
    0.96
    ilty
    0.91
    vable
    0.88
    ased
    0.87
    ivable
    0.87
    antics
    0.85
    ement
    0.84
    assed
    0.83
    uated
    0.82
    Activations Density 0.205%

    No Known Activations