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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21143
    Prev
    Next
    INDEX
    Explanations

    words related to currencies or symbols, such as 'â' and 'Ĥ'

    oai_token-act-pair · gpt-3.5-turbo

    currency symbols and related financial terms

    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
    hattan
    -0.72
     Tid
    -0.71
    wagen
    -0.70
     Shed
    -0.69
     Widow
    -0.68
     Sakuya
    -0.67
    WARD
    -0.66
     Moody
    -0.65
     Trafford
    -0.65
     Rhodes
    -0.65
    POSITIVE LOGITS
    Ħ¢
    1.30
    Ĥª
    1.28
    ĵ
    1.15
    ł
    1.15
    Ĥ
    1.10
    ķ
    1.09
    Ħ
    1.09
    ļ
    1.07
    ŀ
    1.04
    ¥ŀ
    1.04
    Activations Density 0.004%

    No Known Activations