© 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. 1422
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names and terms, particularly related to individuals and institutions

    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
    itia
    -0.73
    gered
    -0.73
    Ïĥ
    -0.72
    kt
    -0.71
    unal
    -0.71
    vent
    -0.69
    !/
    -0.66
    pipe
    -0.66
     Jere
    -0.65
    vg
    -0.64
    POSITIVE LOGITS
     McMaster
    1.06
     McGill
    1.01
    ulty
    0.96
    donald
    0.88
    awar
    0.88
    HAEL
    0.85
    enzie
    0.83
    ourses
    0.76
     Uni
    0.75
     Canad
    0.74
    Activations Density 0.005%

    No Known Activations