© 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. 7059
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing actions or states

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "has been" 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
    izable
    -0.85
    terday
    -0.72
    ][/
    -0.72
    now
    -0.71
    rouse
    -0.70
    ulence
    -0.66
    anges
    -0.64
    whether
    -0.63
    soon
    -0.63
    real
    -0.62
    POSITIVE LOGITS
     outspoken
    1.08
     criticized
    1.03
     steadily
    1.02
     dogged
    1.00
     criticised
    0.99
     plagued
    0.99
     waging
    0.98
     unable
    0.97
    avering
    0.95
     embroiled
    0.94
    Activations Density 0.116%

    No Known Activations