© 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. 8-RES-JB
    11. 24038
    Prev
    Next
    INDEX
    Explanations

    references to controversial political and social topics expressed in heated or passionate language

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words related to systemic inequalities or social issues

    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
     tentative
    -0.72
     earliest
    -0.71
     circadian
    -0.70
     satell
    -0.69
     lineup
    -0.69
    ipolar
    -0.64
     schedule
    -0.64
     synthes
    -0.63
     explor
    -0.63
     formally
    -0.63
    POSITIVE LOGITS
    Then
    1.14
    Similarly
    1.13
    Likewise
    1.12
     Similarly
    1.06
     Then
    1.04
     Likewise
    1.03
     Needless
    1.02
    Laughs
    0.99
    Secondly
    0.97
     etc
    0.97
    Activations Density 0.671%

    No Known Activations