© 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. 23980
    Prev
    Next
    INDEX
    Explanations

    phrases containing the string "ika"

    oai_token-act-pair · gpt-3.5-turbo

    proper names related to individuals

    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
    ĻĤ
    -0.86
     corrid
    -0.84
    ensible
    -0.78
     glim
    -0.77
    uctor
    -0.76
    */(
    -0.74
    dit
    -0.72
    lying
    -0.72
     rall
    -0.71
    parent
    -0.69
    POSITIVE LOGITS
    ika
    1.22
    ppa
    0.87
    issance
    0.85
    izu
    0.84
    uchi
    0.84
    Å¡
    0.84
    emia
    0.83
    qa
    0.82
    ikan
    0.81
    ichi
    0.81
    Activations Density 0.006%

    No Known Activations