© 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. 9437
    Prev
    Next
    INDEX
    Explanations

    words related to published works or academic studies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "published."

    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
    aho
    -0.80
    nea
    -0.80
    xa
    -0.77
    llan
    -0.76
    hart
    -0.76
    atra
    -0.75
    avery
    -0.73
    ichael
    -0.72
    ascar
    -0.72
    uppet
    -0.72
    POSITIVE LOGITS
    lishing
    1.23
    lisher
    1.13
    published
    1.02
     published
    1.00
     publication
    0.98
     publishes
    0.96
     behavi
    0.94
    lishes
    0.93
     RELE
    0.92
    DragonMagazine
    0.91
    Activations Density 0.022%

    No Known Activations