Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 16941
    Prev
    Next
    INDEX
    Explanations

    proper names and surnames, associated with specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those involved in a notable incident or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbn
    -0.87
    Georg
    -0.83
    ARK
    -0.83
    ãĥĩãĤ£
    -0.82
    fare
    -0.80
    udeb
    -0.78
    ymm
    -0.73
    inent
    -0.73
    onyms
    -0.72
    byter
    -0.72
    POSITIVE LOGITS
     Alvarez
    1.10
     Ramirez
    1.08
     Gutierrez
    1.05
     Ventura
    1.03
     Ortiz
    1.01
     Herrera
    0.95
     Gonzalez
    0.92
     Flores
    0.92
     Diaz
    0.90
    irez
    0.89
    Activations Density 0.012%

    No Known Activations