© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2695
    Prev
    Next
    INDEX
    Explanations

    phrases referring to opinions or actions expressed by a particular source

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "More" in various contexts, often relating to emphasis or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.84
    ãĤ©
    -0.73
     Columb
    -0.66
    Reviewer
    -0.66
    Lear
    -0.66
     Shining
    -0.65
     Gum
    -0.65
    ãĥĨãĤ£
    -0.64
    itar
    -0.63
    =-=-=-=-=-=-=-=-
    -0.63
    POSITIVE LOGITS
     confid
    0.73
     Jr
    0.72
     allies
    0.71
    iciary
    0.70
     Republican
    0.69
     aide
    0.68
     strategist
    0.67
     ally
    0.66
     administration
    0.66
     Republicans
    0.66
    Activations Density 0.029%

    No Known Activations