© 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. 9431
    Prev
    Next
    INDEX
    Explanations

    names of individuals, specifically those containing the string "Yosh" or "Shim"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those named Yoshida or Shim

    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
     Scotia
    -0.74
     Psychiatric
    -0.70
    ilogy
    -0.68
    balance
    -0.68
    roads
    -0.67
    feeding
    -0.66
     Addiction
    -0.65
     Lyme
    -0.65
     Loaded
    -0.65
    Berry
    -0.64
    POSITIVE LOGITS
    amoto
    1.22
    ikawa
    1.17
    asaki
    1.13
    azaki
    1.13
    imura
    1.04
    atsu
    1.03
    aido
    1.03
    oka
    0.99
     Yosh
    0.99
    ihara
    0.98
    Activations Density 0.012%

    No Known Activations