© 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. 9-RES-JB
    11. 16048
    Prev
    Next
    INDEX
    Explanations

    mentions of news and media outlets, particularly NPR and PBS

    oai_token-act-pair · gpt-3.5-turbo

    mentions of NPR and its related entities

    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
     Emirates
    -0.73
    wagen
    -0.71
     Mata
    -0.70
    aneously
    -0.68
    clave
    -0.66
    uay
    -0.65
     Jol
    -0.65
     Santos
    -0.63
     Bowser
    -0.62
    initialized
    -0.60
    POSITIVE LOGITS
    NPR
    1.07
     NPR
    0.97
     Transcript
    0.83
     transcripts
    0.83
    nw
    0.76
    rawdownloadcloneembedreportprint
    0.76
    IC
    0.73
    DEF
    0.73
    OVA
    0.70
    NEWS
    0.70
    Activations Density 0.023%

    No Known Activations