© 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. 6598
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "From what" and "what I can" or "we can" indicating making observations or inferences

    oai_token-act-pair · gpt-3.5-turbo

    references to personal observations and experiences

    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
     srfAttach
    -0.60
    powers
    -0.58
    AND
    -0.58
    deals
    -0.57
     grandchildren
    -0.54
    ãĤ³
    -0.54
    èĢħ
    -0.53
    ]=
    -0.52
     Flavoring
    -0.52
    å°Ĩ
    -0.52
    POSITIVE LOGITS
     we
    1.15
     I
    1.03
     seen
    0.90
     pictured
    0.90
    liest
    0.86
     ours
    0.83
     you
    0.81
     imaginable
    0.80
     discussed
    0.79
     mentioned
    0.79
    Activations Density 0.484%

    No Known Activations