© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 3695
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Luigi" in a text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "lu" in various contexts

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

    No Comments

    Negative Logits
    grounds
    -0.77
     Dispatch
    -0.75
     Mavericks
    -0.72
     DPR
    -0.70
    Reviewed
    -0.68
    sburg
    -0.65
    ãģĨ
    -0.64
     WS
    -0.64
     Skydragon
    -0.63
     Limits
    -0.63
    POSITIVE LOGITS
    etooth
    1.32
    igi
    1.09
    orescent
    1.06
    orescence
    0.98
    cius
    0.97
    encers
    0.97
    pton
    0.97
    nder
    0.95
    cci
    0.94
    vre
    0.93
    Activations Density 0.008%

    No Known Activations