© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14008
    Prev
    Next
    INDEX
    Explanations

    sports teams and their current standings or achievements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms and 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
    %%%%
    -0.66
    ":[{"
    -0.66
    hoe
    -0.65
     appl
    -0.64
     document
    -0.63
    Demand
    -0.63
    omm
    -0.62
    relation
    -0.62
    Act
    -0.62
     sar
    -0.62
    POSITIVE LOGITS
     unbeaten
    1.45
     undefeated
    1.42
     contenders
    1.07
     reeling
    1.03
     fortunate
    1.03
     ranked
    1.02
     unbeat
    1.00
     playoff
    0.99
     favourites
    0.98
     averaging
    0.97
    Activations Density 0.155%

    No Known Activations