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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-RES-JB
    6. 24256
    Prev
    Next
    INDEX
    Explanations

    special characters in foreign languages or mathematical notations

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, particularly those that might denote breaks or separations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    milo
    -0.75
     recourse
    -0.72
     dispatcher
    -0.68
    alien
    -0.67
     authorized
    -0.66
    rero
    -0.65
     interf
    -0.64
    ngth
    -0.62
     deaf
    -0.61
     desired
    -0.60
    POSITIVE LOGITS
    ·
    1.47
    é¾į
    1.06
    ´
    1.06
    ¸
    1.04
    ±
    1.03
    µ
    1.01
    ر
    0.98
    į
    0.98
    в
    0.98
    º
    0.97
    Activations Density 0.004%

    No Known Activations