© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9753
    Prev
    Next
    INDEX
    Explanations

    questions with a specific structure involving the word "Does" or "Are"

    oai_token-act-pair · gpt-3.5-turbo

    questions starting with "Does," "Are," or "Is" indicating inquiry or probing into a topic

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

    No Comments

    Negative Logits
    amps
    -0.75
    ãģĮ
    -0.74
    Ñģ
    -0.74
    ãģ«
    -0.72
    ulates
    -0.71
    natureconservancy
    -0.70
    ITH
    -0.68
    ãģ§
    -0.68
    ãĤĴ
    -0.66
    amp
    -0.65
    POSITIVE LOGITS
    olated
    0.72
    olate
    0.71
    nt
    0.70
    ĪĴ
    0.66
     loser
    0.62
     millenn
    0.62
    eday
    0.62
     nomine
    0.62
    aston
    0.61
     subsequ
    0.60
    Activations Density 0.102%

    No Known Activations