© 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. 20060
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to historical significance

    oai_token-act-pair · gpt-3.5-turbo

    references to historical significance or context

    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
    tein
    -0.89
    board
    -0.77
    pool
    -0.77
    mail
    -0.73
    lain
    -0.72
    PT
    -0.70
    plan
    -0.70
    ding
    -0.69
    gur
    -0.68
    yl
    -0.68
    POSITIVE LOGITS
    orically
    1.12
     conduc
    0.87
     resil
    0.85
     historically
    0.82
     accur
    0.81
    ãĤ©
    0.81
    orical
    0.80
     compr
    0.78
    urally
    0.78
     dexter
    0.77
    Activations Density 0.005%

    No Known Activations