© 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. 11623
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving rewards or consequences based on actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal empowerment and individual responsibility

    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
    earch
    -0.76
    oly
    -0.71
    enne
    -0.70
    scroll
    -0.70
    Favorite
    -0.68
    UGE
    -0.68
    Scroll
    -0.68
    Feature
    -0.67
    Flight
    -0.66
    gran
    -0.64
    POSITIVE LOGITS
     unwittingly
    1.41
     inadvertently
    1.37
     implicitly
    1.30
     thereby
    1.23
     indirectly
    1.22
     tacit
    1.17
     depri
    1.16
     unintentionally
    1.16
     legitim
    1.11
     perpet
    1.06
    Activations Density 0.259%

    No Known Activations