© 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. 10215
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to endorsements, opinions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    combinations of conjunctions or phrases that indicate lists or series

    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
    Actor
    -0.62
     Starts
    -0.61
    ,
    -0.60
    uces
    -0.60
    STON
    -0.59
    !/
    -0.57
    Enlarge
    -0.57
     (>
    -0.56
    -,
    -0.55
    worldly
    -0.55
    POSITIVE LOGITS
     are
    1.29
     have
    1.18
     were
    1.17
     deserve
    1.16
    have
    1.10
     aren
    1.10
     seem
    1.07
     constitute
    1.07
     appear
    1.07
    were
    1.06
    Activations Density 0.169%

    No Known Activations