© 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. 7-RES-JB
    11. 11204
    Prev
    Next
    INDEX
    Explanations

    words related to importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    key terms associated with importance or centrality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancies
    -0.87
    onies
    -0.76
    iencies
    -0.75
    atism
    -0.73
    apses
    -0.72
    opes
    -0.71
     curls
    -0.70
    events
    -0.70
    rants
    -0.69
     Syndrome
    -0.68
    POSITIVE LOGITS
     contributor
    1.11
     source
    1.06
    stay
    1.04
     indicator
    1.02
     fixture
    1.00
     contender
    0.99
     deterrent
    0.99
     staple
    0.96
     centerpiece
    0.95
     predictor
    0.95
    Activations Density 0.140%

    No Known Activations