© 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. 9-RES-JB
    11. 17669
    Prev
    Next
    INDEX
    Explanations

    mentions of specific media outlets or publications

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Globe" or related terms

    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
    DER
    -0.84
    amac
    -0.84
    ramid
    -0.81
    wagen
    -0.81
    noon
    -0.78
    oÄŁ
    -0.77
    halla
    -0.76
    crew
    -0.75
    pee
    -0.74
    creen
    -0.73
    POSITIVE LOGITS
     Scotia
    0.91
     Globe
    0.75
    vernment
    0.71
     Lauder
    0.70
    ophone
    0.67
     Carbuncle
    0.67
    Ħ¢
    0.67
     Lakes
    0.65
    ophile
    0.65
     foss
    0.63
    Activations Density 0.094%

    No Known Activations