© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1104
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and political advocacy

    oai_token-act-pair · gpt-3.5-turbo

    processes and policies related to social justice and empowerment efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seconds
    -0.88
    agos
    -0.76
     Detail
    -0.75
    wow
    -0.75
    Legend
    -0.73
    uffer
    -0.73
    ptoms
    -0.72
    eared
    -0.72
    ilty
    -0.72
    »Ĵ
    -0.71
    POSITIVE LOGITS
     boycot
    1.32
     coercion
    1.23
     taxation
    1.20
     lobbying
    1.18
     subsidies
    1.18
     educating
    1.17
     privatization
    1.17
     persuasion
    1.16
     coercive
    1.15
     intimidation
    1.12
    Activations Density 0.401%

    No Known Activations