© 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. 24083
    Prev
    Next
    INDEX
    Explanations

    HTML or special characters within text, especially the symbol "âĢĵ"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific symbol or character denoted by "âĢĵ"

    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
    ©¶æ
    -0.78
     aquarium
    -0.74
     exting
    -0.74
     proportion
    -0.73
     overpowered
    -0.73
    pping
    -0.73
     drains
    -0.73
     drain
    -0.72
    pped
    -0.72
     womb
    -0.72
    POSITIVE LOGITS
    ––
    1.42
    âĸº
    1.00
    ————
    0.97
    ——
    0.96
    ————————
    0.89
    ————————————————
    0.88
    Tenn
    0.81
    =-=-=-=-
    0.78
    Maria
    0.76
     Flavoring
    0.76
    Activations Density 0.092%

    No Known Activations