© 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. 0-RES-JB
    11. 20323
    Prev
    Next
    INDEX
    Explanations

    names or titles ending with "ji"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ji"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     substances
    -0.67
     additive
    -0.63
     ATL
    -0.63
     Virgin
    -0.62
    WIND
    -0.61
     AL
    -0.59
     PACs
    -0.59
     clot
    -0.59
     exceeding
    -0.58
     COP
    -0.58
    POSITIVE LOGITS
    ji
    4.27
    jee
    2.14
    oji
    1.63
    iji
    1.47
    ja
    1.46
    jo
    1.45
    ichi
    1.40
    jing
    1.40
    shi
    1.37
    jit
    1.36
    Activations Density 0.010%

    No Known Activations