© 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. 4895
    Prev
    Next
    INDEX
    Explanations

    phrases related to establishing committees, programs, or funds

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the establishment of plans, committees, or councils for various purposes

    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
     glances
    -0.73
    quickShipAvailable
    -0.66
     smiles
    -0.64
    typ
    -0.63
     gestures
    -0.62
    standing
    -0.60
    lets
    -0.59
     wastes
    -0.58
     clicks
    -0.58
     blockers
    -0.58
    POSITIVE LOGITS
     commemorate
    1.36
     promote
    1.27
     coincide
    1.25
     ensure
    1.22
     determine
    1.19
     celebrate
    1.15
     facilitate
    1.14
     accompany
    1.13
     conserve
    1.12
     enhance
    1.11
    Activations Density 0.237%

    No Known Activations