Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21467
    Prev
    Next
    INDEX
    Explanations

    words containing special characters like "ı" and "ÅŁ"

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters or letters in a specific context

    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
     Appalach
    -0.84
    arsity
    -0.72
     Sussex
    -0.70
     guiActiveUnfocused
    -0.69
     Spartan
    -0.67
    Buyable
    -0.66
     Willow
    -0.66
     HMS
    -0.66
    maxwell
    -0.65
     Indigo
    -0.65
    POSITIVE LOGITS
    ı
    1.06
    ¶
    1.01
    Ì
    1.01
    oÄŁ
    0.99
    ·
    0.97
    ÅŁ
    0.95
    ¾
    0.94
    Ķ
    0.88
    ĥ
    0.87
    Ĩ
    0.86
    Activations Density 0.010%

    No Known Activations