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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16410
    Prev
    Next
    INDEX
    Explanations

    locating mentions of a high level of concentration or focus within a specific context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "concentrated" and its variations

    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
    named
    -0.79
    anne
    -0.75
    ne
    -0.71
    ĪĴ
    -0.70
    RESULTS
    -0.67
    posted
    -0.67
    look
    -0.67
    hide
    -0.66
    ears
    -0.65
    lyn
    -0.64
    POSITIVE LOGITS
     concentrated
    1.01
     concentration
    0.86
     concentrate
    0.86
     concentrating
    0.86
    iple
    0.82
     concent
    0.81
     Concent
    0.78
    erto
    0.76
    itures
    0.75
    glomer
    0.74
    Activations Density 0.014%

    No Known Activations