© 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. 418
    Prev
    Next
    INDEX
    Explanations

    instances of the mention of paid or administrative leave

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "leave" in various contexts related to employment and absence

    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
     Flavoring
    -0.82
    ãĥ´
    -0.72
    sonian
    -0.72
    SOURCE
    -0.69
    Appearance
    -0.69
     Seym
    -0.68
     neighb
    -0.68
    ãĤ¢ãĥ«
    -0.67
     ancest
    -0.66
     behavi
    -0.66
    POSITIVE LOGITS
    utic
    0.99
     entitle
    0.91
    away
    0.83
     parole
    0.80
     obligations
    0.77
    vation
    0.76
     Sched
    0.72
     leave
    0.71
     allowance
    0.70
     therapists
    0.70
    Activations Density 0.047%

    No Known Activations