Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23621
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "Ika", potentially a specific term or name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific fruit or dish, particularly "sudachi" and "sudachi bagel."

    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
    Merit
    -0.70
     mill
    -0.65
     prox
    -0.64
     resp
    -0.63
     rect
    -0.63
     defe
    -0.63
     typew
    -0.61
     forb
    -0.61
     permitting
    -0.60
    PIN
    -0.60
    POSITIVE LOGITS
    ika
    4.45
    iki
    1.75
    ik
    1.68
    ica
    1.62
    ikan
    1.51
    ikk
    1.51
    ique
    1.49
    IK
    1.48
    iko
    1.45
    akia
    1.40
    Activations Density 0.011%

    No Known Activations