© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 17457
    Prev
    Next
    INDEX
    Explanations

    mentions of news organizations and journalists

    oai_token-act-pair · gpt-3.5-turbo

    references to news organizations and their reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.71
     bragging
    -0.68
    comed
    -0.68
    ¯
    -0.64
    blogspot
    -0.63
    tumblr
    -0.62
    ãĥĹ
    -0.61
     fasc
    -0.58
     perenn
    -0.57
     Confederate
    -0.57
    POSITIVE LOGITS
     correspondent
    0.78
     Investigative
    0.73
     obtained
    0.68
     investigation
    0.67
    ENE
    0.65
    yssey
    0.65
     understands
    0.64
    Asia
    0.64
     Probe
    0.64
     compr
    0.63
    Activations Density 0.123%

    No Known Activations