© 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. 8-RES-JB
    11. 22456
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency-related terms

    oai_token-act-pair · gpt-3.5-turbo

    specific acronyms and organizational names related to financial or corporate entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idays
    -0.70
    ¯
    -0.69
     toget
    -0.67
    ovych
    -0.66
    CLASS
    -0.64
    ibling
    -0.64
     flo
    -0.64
    accompan
    -0.61
     tremend
    -0.59
    ahime
    -0.58
    POSITIVE LOGITS
    ulhu
    1.10
    ioxide
    0.86
    ornia
    0.85
     Unch
    0.81
    ortium
    0.79
    xus
    0.76
    aign
    0.72
    ierre
    0.72
    arette
    0.70
    ERA
    0.69
    Activations Density 0.573%

    No Known Activations