© 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. 370
    Prev
    Next
    INDEX
    Explanations

    instances where something is considered problematic or controversial

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to disagreement or opposition

    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
    interstitial
    -0.73
    ioned
    -0.73
    icter
    -0.72
     exting
    -0.68
    weeney
    -0.68
    wich
    -0.67
    hei
    -0.66
    wake
    -0.66
    ocene
    -0.64
    ewater
    -0.64
    POSITIVE LOGITS
     nor
    0.93
     anybody
    0.92
     anyone
    0.80
     anymore
    0.73
     either
    0.72
     anything
    0.70
     Explorer
    0.67
     enjoyment
    0.65
     or
    0.64
     temptation
    0.63
    Activations Density 0.275%

    No Known Activations