© 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. 4-RES-JB
    11. 7037
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tell"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "can tell."

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

    No Comments

    Negative Logits
    cdn
    -0.88
    urdue
    -0.74
    Merit
    -0.72
    amic
    -0.70
    imposed
    -0.66
    rane
    -0.66
    egal
    -0.65
    Hung
    -0.64
    engeance
    -0.63
    Naz
    -0.63
    POSITIVE LOGITS
    tale
    1.33
    ingly
    1.01
    tell
    0.89
    ariat
    0.82
     tell
    0.73
    ysis
    0.71
    about
    0.68
     Leilan
    0.66
     Tell
    0.66
     anecd
    0.66
    Activations Density 0.031%

    No Known Activations