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. 7-RES-JB
    6. 1378
    Prev
    Next
    INDEX
    Explanations

    phrases signaling a change in topic or emphasizing a statement as important

    oai_token-act-pair · gpt-3.5-turbo

    introductory phrases or clauses that set a context for the following statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiName
    -0.95
    ãĢİ
    -0.80
    conservancy
    -0.77
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    wcs
    -0.74
    foreseen
    -0.73
    etheless
    -0.72
    merce
    -0.70
    --------------------------------------------------------
    -0.69
    taboola
    -0.68
    POSITIVE LOGITS
    !)
    1.40
    ?)
    1.38
    .)
    1.37
    )"
    1.33
    )."
    1.31
    -)
    1.30
    â̦)
    1.28
    +)
    1.28
    )
    1.20
    ),"
    1.18
    Activations Density 0.110%

    No Known Activations