© 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. 6-RES-JB
    11. 14424
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or calls to action within text

    oai_token-act-pair · gpt-3.5-turbo

    calls to action encouraging resource exploration or information access

    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
    vernment
    -0.72
     destro
    -0.71
    */(
    -0.66
    ãĥĻ
    -0.65
    ciating
    -0.64
    cept
    -0.62
    essed
    -0.62
    æѦ
    -0.61
     peripher
    -0.61
    kered
    -0.61
    POSITIVE LOGITS
     Contact
    0.69
    asia
    0.65
    ande
    0.64
     Adobe
    0.62
     Preservation
    0.62
     Hemp
    0.59
     Ov
    0.57
    contact
    0.56
     Dice
    0.56
     AFC
    0.56
    Activations Density 0.112%

    No Known Activations