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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 6998
    Prev
    Next
    INDEX
    Explanations

    mentions of specific newspapers and news outlets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific publications and newspapers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     installations
    -0.71
    pty
    -0.67
    packs
    -0.66
    HUD
    -0.65
    falls
    -0.61
    thood
    -0.61
    acca
    -0.60
     silhou
    -0.60
    chwitz
    -0.60
     fans
    -0.58
    POSITIVE LOGITS
     Herald
    1.24
     Observer
    1.17
     Times
    1.17
     Telegraph
    1.14
     Tribune
    1.14
     Gazette
    1.13
     Examiner
    1.10
     Journal
    1.10
     Chronicle
    1.07
     Courier
    1.07
    Activations Density 0.146%

    No Known Activations