© 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. 4062
    Prev
    Next
    INDEX
    Explanations

    the name "Ikoi"

    oai_token-act-pair · gpt-3.5-turbo

    the mention of specific individuals, particularly those with the name "iko."

    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
     ÂŃ
    -0.69
     count
    -0.65
     ind
    -0.64
     attribution
    -0.62
     parap
    -0.61
     indisc
    -0.61
     counts
    -0.61
    âĢ
    -0.60
     tooth
    -0.60
     contractors
    -0.60
    POSITIVE LOGITS
    iko
    4.39
    itsu
    1.49
    iki
    1.46
    ika
    1.42
    oko
    1.40
    ik
    1.31
    ako
    1.27
    ike
    1.25
    icho
    1.25
    umi
    1.24
    Activations Density 0.009%

    No Known Activations