© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3525
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where someone is assigned a specific task

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tasked" and similar terms that convey assignment of responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idem
    -0.71
     Geo
    -0.71
    Salt
    -0.70
    alter
    -0.69
    EVA
    -0.67
    Mos
    -0.64
    patch
    -0.63
    alcohol
    -0.63
    leaf
    -0.62
    Lev
    -0.62
    POSITIVE LOGITS
     tasked
    1.33
    naire
    1.00
     entrusted
    0.92
    ioned
    0.86
    ãĥ¼ãĥĨ
    0.83
    ãĥ¼ãĥĨãĤ£
    0.82
     tasks
    0.78
     showc
    0.77
    hower
    0.76
    ngth
    0.76
    Activations Density 0.005%

    No Known Activations