© 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. 0-RES-JB
    11. 22668
    Prev
    Next
    INDEX
    Explanations

    references to the name "Lombardo."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ardo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DEC
    -0.65
     other
    -0.63
     clicks
    -0.62
     Mann
    -0.62
    DEC
    -0.62
     extensions
    -0.61
     others
    -0.61
     liberals
    -0.59
     pur
    -0.59
     OTHER
    -0.58
    POSITIVE LOGITS
    ardo
    4.72
    ard
    1.75
    ardi
    1.67
    ards
    1.64
    ARD
    1.42
    arding
    1.32
    arded
    1.31
    ardy
    1.30
    redo
    1.29
    aldo
    1.27
    Activations Density 0.013%

    No Known Activations