© 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. 3-RES-JB
    11. 11508
    Prev
    Next
    INDEX
    Explanations

    mentions where something is purely a certain way or purely focused on a specific attribute

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the word "purely."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Colleges
    -0.81
     Cards
    -0.78
     Mushroom
    -0.78
     Nurs
    -0.73
    lain
    -0.72
     Seeds
    -0.71
     Neighbor
    -0.69
     Peninsula
    -0.68
     Oaks
    -0.68
    velt
    -0.68
    POSITIVE LOGITS
    technical
    0.84
    rative
    0.82
    reet
    0.80
     minded
    0.77
     purely
    0.77
     guiActiveUn
    0.73
    initions
    0.72
     nil
    0.69
    wcsstore
    0.69
    =#
    0.69
    Activations Density 0.003%

    No Known Activations