© 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. 22522
    Prev
    Next
    INDEX
    Explanations

    phrases introducing specific cases or examples

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in the case of" or variations thereof

    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
    undo
    -0.74
    å°Ĩ
    -0.66
     pier
    -0.66
     brill
    -0.64
    ient
    -0.62
    talk
    -0.61
    sle
    -0.61
    ascus
    -0.60
    reed
    -0.60
    dep
    -0.59
    POSITIVE LOGITS
     exception
    0.66
     Admission
    0.64
     negligence
    0.64
     Ep
    0.64
    cases
    0.63
    dinand
    0.62
    rarily
    0.62
    ambers
    0.62
     Case
    0.62
    rosso
    0.61
    Activations Density 0.097%

    No Known Activations