© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 18108
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a specific media company

    oai_token-act-pair · gpt-3.5-turbo

    references to CBS News

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.68
    oin
    -0.68
     realise
    -0.67
    layer
    -0.66
    hops
    -0.66
     armour
    -0.66
    isl
    -0.63
     «
    -0.62
    imir
    -0.62
    ierre
    -0.61
    POSITIVE LOGITS
     CBS
    3.59
    CBS
    2.86
     NBC
    2.15
     ABC
    1.93
     FOX
    1.82
    NBC
    1.66
     PBS
    1.64
    ABC
    1.61
     CNN
    1.57
    FOX
    1.55
    Activations Density 0.019%

    No Known Activations