© 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. 6-RES-JB
    11. 9598
    Prev
    Next
    INDEX
    Explanations

    words related to completion or finalization of tasks or projects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the words "finish" and "finished."

    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
    elled
    -0.83
    uli
    -0.81
    esis
    -0.69
    hare
    -0.68
    resy
    -0.68
    gravity
    -0.67
    orum
    -0.65
    recogn
    -0.64
    err
    -0.64
    uru
    -0.63
    POSITIVE LOGITS
     unfinished
    0.83
     touches
    0.80
    housing
    0.72
     preparations
    0.68
    ãĤ¤ãĥĪ
    0.68
    teness
    0.67
     finishing
    0.64
     arming
    0.63
     uninterrupted
    0.62
    âĶĢâĶĢ
    0.62
    Activations Density 0.026%

    No Known Activations