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

    Neuronpedia

    Jacobian LensNEW
    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. 3414
    Prev
    Next
    INDEX
    Explanations

    names of individuals with varying levels of importance or relevance

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and their affiliations

    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
     Presidents
    -0.69
    soDeliveryDate
    -0.64
    /-
    -0.58
     phase
    -0.57
    STATE
    -0.57
    Except
    -0.57
    Council
    -0.57
     stabilization
    -0.56
     deregulation
    -0.56
     presumptive
    -0.55
    POSITIVE LOGITS
     agrees
    0.98
     joins
    0.98
     commented
    0.97
     told
    0.96
     wrote
    0.94
     believes
    0.91
     testified
    0.89
     welcomed
    0.88
    icz
    0.87
    vich
    0.87
    Activations Density 0.300%

    No Known Activations