© 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. 6-RES-JB
    11. 17604
    Prev
    Next
    INDEX
    Explanations

    political terms and survey-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    demographic data regarding political affiliations and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     graft
    -0.80
     salvage
    -0.78
     cloning
    -0.75
     manufact
    -0.74
     cabal
    -0.74
     rehab
    -0.73
     malf
    -0.70
    ulence
    -0.70
     scramble
    -0.70
     malfunction
    -0.70
    POSITIVE LOGITS
     polled
    1.09
     surveyed
    1.09
     respondents
    1.01
    agree
    0.99
     Gallup
    0.95
     undecided
    0.87
    avorable
    0.84
     respondent
    0.83
    aukee
    0.83
     Pew
    0.80
    Activations Density 0.505%

    No Known Activations