© 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. 2-RES-JB
    11. 1022
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the names "Marty" and "Gloria"

    oai_token-act-pair · gpt-4-turbo

    proper names, particularly the name "Marty", with a very high activation value

    oai_token-act-pair · gpt-3.5-turbo

    the name "Marty" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alez
    -0.96
    ngth
    -0.87
    intent
    -0.85
    sembly
    -0.84
    edIn
    -0.83
    otin
    -0.82
    umbnail
    -0.81
    awaru
    -0.80
    pir
    -0.78
    nel
    -0.78
    POSITIVE LOGITS
     Marty
    1.29
     Feldman
    0.90
     McMahon
    0.89
     Mart
    0.86
     Chandler
    0.85
     Vince
    0.84
     Dino
    0.81
     Stanley
    0.81
     Mc
    0.81
     Markus
    0.80
    Activations Density 0.007%

    No Known Activations