© 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. 8-RES-JB
    11. 10799
    Prev
    Next
    INDEX
    Explanations

    references related to political and military events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partName
    -0.66
     Folder
    -0.64
    :(
    -0.61
     ********************************
    -0.58
     Cous
    -0.56
    laughs
    -0.56
    aeper
    -0.55
    :[
    -0.55
     Verse
    -0.55
    âĶĢâĶĢâĶĢâĶĢ
    -0.55
    POSITIVE LOGITS
     amid
    0.78
     crackdown
    0.77
     austerity
    0.74
    AFP
    0.71
     blamed
    0.67
     deadliest
    0.64
     fears
    0.64
     AFP
    0.63
    Reuters
    0.62
     bailout
    0.62
    Activations Density 1.426%

    No Known Activations