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. 6-RES-JB
    6. 19842
    Prev
    Next
    INDEX
    Explanations

    mentions of company abbreviations or acronyms

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or abbreviations related to organizations, agencies, or specific designations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    panic
    -0.71
     thous
    -0.71
     surpr
    -0.67
    ogene
    -0.66
    taboola
    -0.65
    ãĥĥãĥī
    -0.63
    enegger
    -0.63
     gru
    -0.63
    depending
    -0.62
     speedy
    -0.62
    POSITIVE LOGITS
    HY
    0.95
    FU
    0.95
    KI
    0.89
    KA
    0.89
    Z
    0.82
    NP
    0.82
    ESH
    0.82
    KT
    0.82
    GS
    0.82
    ZE
    0.81
    Activations Density 0.134%

    No Known Activations