© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 2414
    Prev
    Next
    INDEX
    Explanations

    phrases related to different media outlets and news sources, particularly The Daily Mail and The Daily Caller

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific news outlets, particularly the Daily Mail and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gone
    -0.73
    worldly
    -0.72
    inant
    -0.71
    heric
    -0.70
    actionDate
    -0.68
     rall
    -0.66
    lease
    -0.66
    NetMessage
    -0.65
    ĪĴ
    -0.65
    unity
    -0.64
    POSITIVE LOGITS
     Newsp
    0.87
     Gazette
    0.86
    Leaks
    0.84
     Digest
    0.82
     Publishing
    0.81
     Editorial
    0.80
     Foundation
    0.77
    Truth
    0.77
     News
    0.75
     newspaper
    0.75
    Activations Density 0.036%

    No Known Activations