© 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. 9-RES-JB
    11. 1062
    Prev
    Next
    INDEX
    Explanations

    references to news outlets or publications

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions or references to "The."

    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
     beware
    -0.78
    ionics
    -0.69
    thood
    -0.69
     endeav
    -0.67
     eyeing
    -0.64
     extingu
    -0.64
     tackling
    -0.64
     undergo
    -0.63
     sidel
    -0.63
     stopping
    -0.62
    POSITIVE LOGITS
     Huffington
    1.41
     Guardian
    1.20
     Verge
    1.17
     Associated
    1.16
     Economist
    1.15
     Conversation
    1.15
     Daily
    1.14
     Chronicle
    1.12
     Telegraph
    1.09
     Observer
    1.05
    Activations Density 0.052%

    No Known Activations