© 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. 1414
    Prev
    Next
    INDEX
    Explanations

    phrases indicating likelihood or expectation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating likelihood or probability

    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
     pending
    -0.73
     implication
    -0.69
     purportedly
    -0.67
     implies
    -0.67
     denotes
    -0.66
     supposedly
    -0.65
    Broad
    -0.63
     backdrop
    -0.63
     announcing
    -0.61
     allegedly
    -0.59
    POSITIVE LOGITS
    wb
    0.79
     appreciate
    0.79
     reap
    0.77
    .</
    0.76
     envy
    0.75
    Enjoy
    0.75
     enjoy
    0.75
    >.
    0.74
     happier
    0.74
     outper
    0.73
    Activations Density 0.317%

    No Known Activations