© 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. 4-RES-JB
    11. 7824
    Prev
    Next
    INDEX
    Explanations

    names of specific entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of entities, people, or places

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

    No Comments

    Negative Logits
    enegger
    -0.62
    代
    -0.57
     srf
    -0.51
    é¾įå
    -0.51
    senal
    -0.50
    jri
    -0.49
    ãĥ¼ãĥĨ
    -0.49
     Leilan
    -0.48
    outube
    -0.48
    ourke
    -0.48
    POSITIVE LOGITS
    ¶
    0.49
    coin
    0.48
    ÂŃ
    0.44
    going
    0.43
     âĢº
    0.42
     malt
    0.40
     bicycl
    0.39
    Coin
    0.39
     brewers
    0.38
    weed
    0.38
    Activations Density 1.875%

    No Known Activations