© 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. 3924
    Prev
    Next
    INDEX
    Explanations

    names and surnames, specifically focusing on the surnames

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals and entities

    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
    NF
    -0.78
    upuncture
    -0.72
     heartbeat
    -0.72
     ultras
    -0.70
     arrang
    -0.68
    izoph
    -0.67
    omatic
    -0.66
    LIN
    -0.64
    nosis
    -0.62
     characterization
    -0.62
    POSITIVE LOGITS
    nard
    0.91
    pheus
    0.88
    ertodd
    0.84
    xon
    0.82
    ppo
    0.81
    ignty
    0.79
    andr
    0.77
    ternity
    0.77
    fleet
    0.76
    esa
    0.74
    Activations Density 0.037%

    No Known Activations