© 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. 1-RES-JB
    11. 5594
    Prev
    Next
    INDEX
    Explanations

    the verb "penned"

    oai_token-act-pair · gpt-3.5-turbo

    words associated with writing or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assium
    -0.78
    aina
    -0.68
    ift
    -0.68
    asia
    -0.67
    ifted
    -0.67
    EMS
    -0.65
    amd
    -0.65
    Wr
    -0.65
    oro
    -0.64
    ripp
    -0.64
    POSITIVE LOGITS
     penned
    1.57
    lishing
    0.91
     LET
    0.90
     written
    0.87
     scrib
    0.80
    written
    0.74
     arrang
    0.74
     pens
    0.72
    kamp
    0.72
    Writing
    0.71
    Activations Density 0.010%

    No Known Activations