© 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. 10-RES-JB
    11. 11468
    Prev
    Next
    INDEX
    Explanations

    actions or tasks that are being performed

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "carried out" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esa
    -0.67
    untled
    -0.63
     Enlight
    -0.60
    Bee
    -0.60
    bies
    -0.57
     SLI
    -0.56
    eeks
    -0.56
    Pie
    -0.56
    Crew
    -0.55
     Pie
    -0.52
    POSITIVE LOGITS
    out
    0.83
    ĸļ
    0.79
    forward
    0.79
    over
    0.78
     forward
    0.78
    hani
    0.76
    phrase
    0.75
    Ô
    0.75
    weight
    0.72
    ¶æ
    0.72
    Activations Density 0.026%

    No Known Activations