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. 8-RES-JB
    6. 5954
    Prev
    Next
    INDEX
    Explanations

    words related to technology and abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations, acronyms, or codes

    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
    assetsadobe
    -0.86
     eleph
    -0.82
     \'
    -0.81
     tradem
    -0.76
     guiActiveUn
    -0.74
    netflix
    -0.74
    Downloadha
    -0.74
     teasp
    -0.72
    EStream
    -0.71
    uyomi
    -0.71
    POSITIVE LOGITS
    N
    1.18
    B
    1.18
    F
    1.17
    E
    1.14
    O
    1.14
    Y
    1.13
    X
    1.12
    V
    1.11
    FB
    1.09
    Ds
    1.09
    Activations Density 0.080%

    No Known Activations