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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4114
    Prev
    Next
    INDEX
    Explanations

    phrases related to news and media outlets

    oai_token-act-pair · gpt-3.5-turbo

    references to newsletters and news outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.69
    lease
    -0.67
    amazon
    -0.64
    ogun
    -0.64
    Ö¼
    -0.62
    binding
    -0.61
    iland
    -0.60
    ajo
    -0.59
    gone
    -0.59
    inventory
    -0.59
    POSITIVE LOGITS
    sylv
    0.80
     Nights
    0.78
    fm
    0.76
    Truth
    0.75
     Gazette
    0.72
    erity
    0.72
    NEWS
    0.71
    ROR
    0.69
    truth
    0.67
     Weekly
    0.67
    Activations Density 0.077%

    No Known Activations