© 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. 8-RES-JB
    11. 22480
    Prev
    Next
    INDEX
    Explanations

    phrases related to activism, social causes, and political movements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anti campaigns or movements

    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
    ĸļ
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
     Pelicans
    -0.65
     Halls
    -0.65
     Sins
    -0.64
     grapes
    -0.63
    hetti
    -0.62
     Brooks
    -0.62
     Comfort
    -0.61
     Solitaire
    -0.61
    POSITIVE LOGITS
    abortion
    1.13
    establishment
    1.11
    war
    1.07
    hero
    0.97
    strate
    0.94
    -'
    0.87
    measures
    0.86
    inflammatory
    0.84
    overty
    0.84
    attack
    0.84
    Activations Density 0.029%

    No Known Activations