© 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. 11512
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving instructions or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating meaningful actions and their implications

    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
    tein
    -0.74
     Mechdragon
    -0.67
    onom
    -0.62
    ovember
    -0.59
    abase
    -0.58
    OTOS
    -0.58
    ensor
    -0.58
    sonian
    -0.57
    aceae
    -0.55
    coni
    -0.55
    POSITIVE LOGITS
    akings
    0.54
    Ģ
    0.51
    ario
    0.49
     cryst
    0.49
    ese
    0.48
     ra
    0.47
    eal
    0.47
     conclud
    0.46
    «
    0.46
    eed
    0.45
    Activations Density 0.254%

    No Known Activations