© 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. 3-RES-JB
    11. 12199
    Prev
    Next
    INDEX
    Explanations

    syntactic patterns with special characters like "Ŀ"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character 'Ŀ'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conception
    -0.78
     ende
    -0.78
    ufact
    -0.77
     plur
    -0.76
     indictment
    -0.75
     obser
    -0.72
     tangled
    -0.71
     elig
    -0.71
     enrol
    -0.71
    chnology
    -0.70
    POSITIVE LOGITS
    ¯
    0.91
    é¾į
    0.89
    ¼
    0.85
    Ĭ
    0.84
    tab
    0.81
    £
    0.80
    ï¸
    0.79
    log
    0.79
    bryce
    0.79
    âĢł
    0.78
    Activations Density 0.270%

    No Known Activations