© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 14243
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocacy, activism, and legal action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to accountability and complaints, particularly in the context of organizations addressing grievances

    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
     curv
    -0.70
    ());
    -0.68
    ulton
    -0.66
     eternity
    -0.64
     Majesty
    -0.64
     Hitman
    -0.63
     Admir
    -0.62
     Elys
    -0.60
     Colts
    -0.60
    araoh
    -0.60
    POSITIVE LOGITS
     opposes
    1.09
     organizing
    1.08
     boycot
    1.07
     affili
    1.04
     lobbying
    1.03
     boycott
    1.03
     sponsoring
    1.01
     mobilized
    1.00
     advocating
    1.00
     petition
    1.00
    Activations Density 0.664%

    No Known Activations