© 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. 4-RES-JB
    11. 14783
    Prev
    Next
    INDEX
    Explanations

    the character or symbol 'Ŀ'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences 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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ponder
    -0.74
    chnology
    -0.73
     unconscious
    -0.71
     exorc
    -0.71
     incorpor
    -0.68
     floppy
    -0.68
     ultras
    -0.68
     subconscious
    -0.68
     clutch
    -0.67
     orgasm
    -0.66
    POSITIVE LOGITS
    é¾į
    1.08
    ãĤ±
    0.88
    °
    0.87
    âĶģ
    0.84
    ¼
    0.84
    Ĭ
    0.83
    º
    0.83
    º
    0.83
    Ĺ
    0.80
    log
    0.80
    Activations Density 0.173%

    No Known Activations