© 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. 8385
    Prev
    Next
    INDEX
    Explanations

    proper nouns such as locations

    oai_token-act-pair · gpt-3.5-turbo

    place names, particularly focused on "Riverside" and "Irvine."

    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
    ãĥīãĥ©
    -0.79
    Ò
    -0.76
    akia
    -0.74
    obos
    -0.74
    bag
    -0.73
    jamin
    -0.72
    oha
    -0.70
    ochond
    -0.70
    artifacts
    -0.69
    opard
    -0.67
    POSITIVE LOGITS
    lia
    0.88
     Irvine
    0.88
     Byrne
    0.83
     Lect
    0.75
    land
    0.75
    iculture
    0.74
     Riverside
    0.73
    shire
    0.73
    endale
    0.73
    llo
    0.72
    Activations Density 0.022%

    No Known Activations