© 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. 2881
    Prev
    Next
    INDEX
    Explanations

    Japanese names, particularly the surname "Aki."

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of certain names or terms associated with individuals

    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
     dup
    -0.63
     Reflect
    -0.62
     Rack
    -0.62
     disappoint
    -0.61
     Reprodu
    -0.61
     lif
    -0.59
     RB
    -0.59
     inhal
    -0.59
     proc
    -0.57
     plagiar
    -0.57
    POSITIVE LOGITS
    aki
    4.57
    akis
    2.02
    aka
    1.39
    ako
    1.37
    akura
    1.29
    achi
    1.27
    ahi
    1.26
    awa
    1.22
    oka
    1.21
    omi
    1.20
    Activations Density 0.010%

    No Known Activations