© 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. 19565
    Prev
    Next
    INDEX
    Explanations

    Monroe mentions in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "Mon" and variations of that term, likely related to dates or locations referencing Monroe

    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
    ãĤº
    -0.77
     Norn
    -0.77
    avorite
    -0.77
    CU
    -0.71
    éļ
    -0.71
    ENG
    -0.70
    ACTED
    -0.68
     Anaheim
    -0.68
    èĥ
    -0.68
    rating
    -0.67
    POSITIVE LOGITS
    strous
    1.01
    roe
    1.00
    uclear
    0.95
    olithic
    0.94
    ths
    0.91
    itored
    0.91
    ument
    0.87
    fort
    0.82
    stros
    0.82
    ucle
    0.81
    Activations Density 0.014%

    No Known Activations