© 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. 1-RES-JB
    11. 13358
    Prev
    Next
    INDEX
    Explanations

    verb forms that express opinions or sentiments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "expressed" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neys
    -0.78
    dry
    -0.70
    etheless
    -0.68
    fman
    -0.68
    unch
    -0.68
    ellen
    -0.67
    ctors
    -0.66
    ney
    -0.64
    nered
    -0.64
    thin
    -0.63
    POSITIVE LOGITS
     expressed
    0.96
     express
    0.86
     expresses
    0.85
     guiActiveUn
    0.83
     expressing
    0.80
    Quantity
    0.78
    terday
    0.75
    ktop
    0.74
    WER
    0.73
    :]
    0.72
    Activations Density 0.012%

    No Known Activations