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. 3009
    Prev
    Next
    INDEX
    Explanations

    sentences ending with full stops

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey strong opinions or declarations

    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
     trough
    -0.71
     correspond
    -0.64
     quir
    -0.64
     cheek
    -0.63
     sway
    -0.63
    ¶ħ
    -0.62
    zel
    -0.62
    ãĤ´ãĥ³
    -0.61
     officially
    -0.59
     cradle
    -0.59
    POSITIVE LOGITS
     â̦"
    1.34
     Hopefully
    1.25
     Otherwise
    1.20
     Whoever
    1.17
    .")
    1.16
    '"
    1.16
     ..."
    1.14
     Especially
    1.12
     They
    1.11
     There
    1.10
    Activations Density 0.216%

    No Known Activations