© 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. 4-RES-JB
    11. 2906
    Prev
    Next
    INDEX
    Explanations

    phrases related to inclusion or being part of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "included."

    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
    redo
    -0.73
    rait
    -0.70
    thur
    -0.68
    ²¾
    -0.68
    ¯¯¯¯¯¯¯¯
    -0.68
    ethy
    -0.66
    ggles
    -0.65
    aptic
    -0.65
    ingham
    -0.64
    stem
    -0.63
    POSITIVE LOGITS
     prominently
    0.82
    ãĤ´
    0.80
    ãģĨ
    0.75
    ãĤ½
    0.71
    ropolitan
    0.69
     herein
    0.66
    ãĤ¯
    0.66
    dylib
    0.65
    ipher
    0.64
     Included
    0.63
    Activations Density 0.041%

    No Known Activations