© 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. 15425
    Prev
    Next
    INDEX
    Explanations

    locations and events related to news headlines

    oai_token-act-pair · gpt-3.5-turbo

    references to controversial social and political events or entities

    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
    Emer
    -0.70
    à¨
    -0.66
    ":"/
    -0.66
    odder
    -0.63
    keyes
    -0.63
     actionGroup
    -0.62
    erenn
    -0.60
    Ô
    -0.60
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.59
     Defin
    -0.59
    POSITIVE LOGITS
     clashed
    0.81
     alleging
    0.75
     amid
    0.72
     sparked
    0.69
     violates
    0.69
     blamed
    0.67
     slammed
    0.66
     criticised
    0.65
     leaked
    0.65
     Belfast
    0.64
    Activations Density 0.438%

    No Known Activations