© 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. 11-RES-JB
    11. 17106
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "like"

    oai_token-act-pair · gpt-3.5-turbo

    references to similarity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eni
    -0.63
    pai
    -0.54
    cision
    -0.54
    cific
    -0.53
    aband
    -0.53
    ylum
    -0.49
    etts
    -0.49
    resh
    -0.49
    udic
    -0.48
    ñ
    -0.48
    POSITIVE LOGITS
     that
    1.71
    that
    1.62
     THAT
    1.58
    That
    1.43
     That
    1.29
     those
    1.22
    those
    1.07
     thats
    1.03
    Those
    0.93
     Those
    0.83
    Activations Density 1.751%

    No Known Activations