© 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 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. 4-RES-JB
    11. 1832
    Prev
    Next
    INDEX
    Explanations

    mentions of the news publication 'Observer'

    oai_token-act-pair · gpt-3.5-turbo

    references to news organizations and media outlets

    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
    ersen
    -0.96
    romy
    -0.91
    si
    -0.85
    ame
    -0.83
    inav
    -0.81
    alos
    -0.81
    sburgh
    -0.80
    sen
    -0.78
    inning
    -0.78
    esome
    -0.77
    POSITIVE LOGITS
    OPLE
    0.85
    vier
    0.80
    Desk
    0.77
    âĸ¬
    0.77
     Editorial
    0.76
     Mail
    0.75
     Pattern
    0.75
     Advocate
    0.74
     Newspaper
    0.74
     Newsletter
    0.73
    Activations Density 0.053%

    No Known Activations