© 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. 9948
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing gratitude

    oai_token-act-pair · gpt-3.5-turbo

    instances of the sequence "Th" in the text

    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
     clearance
    -0.75
     presented
    -0.69
     vain
    -0.69
     lapse
    -0.68
     backgrounds
    -0.65
     pronounced
    -0.64
     laps
    -0.64
     portfolio
    -0.62
     discounted
    -0.62
     guarding
    -0.61
    POSITIVE LOGITS
    irteen
    1.52
    ousand
    1.45
    ieves
    1.44
    reshold
    1.44
    umbs
    1.42
    ailand
    1.42
    ought
    1.40
    inking
    1.36
    rowing
    1.33
    ats
    1.32
    Activations Density 0.020%

    No Known Activations