© 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. 13185
    Prev
    Next
    INDEX
    Explanations

    references to text being written by someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "written."

    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
    abe
    -0.89
    nel
    -0.89
    ugal
    -0.80
    Ĭ±
    -0.76
    elli
    -0.74
    MAL
    -0.72
    alo
    -0.71
    alm
    -0.71
    alin
    -0.70
    aho
    -0.70
    POSITIVE LOGITS
     written
    0.81
     penned
    0.74
     essays
    0.74
     excerpts
    0.73
     breath
    0.71
     compositions
    0.71
    smanship
    0.71
     writing
    0.70
    writing
    0.69
     composing
    0.69
    Activations Density 0.027%

    No Known Activations