© 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. 3-RES-JB
    11. 2834
    Prev
    Next
    INDEX
    Explanations

    terms related to political issues, such as anti-smoking, anti-government, anti-immigrant, and anti-war, with a particular focus on certain groups or actions within these broader categories

    oai_token-act-pair · gpt-3.5-turbo

    references to anti-establishment or anti-authority sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å·
    -0.70
    iosis
    -0.68
     srfAttach
    -0.67
     FANTASY
    -0.66
    GREEN
    -0.65
    LESS
    -0.63
     STATS
    -0.63
    rawdownloadcloneembedreportprint
    -0.61
    VILLE
    -0.59
    IENCE
    -0.58
    POSITIVE LOGITS
    xiety
    0.84
    heid
    0.82
    byter
    0.82
    amation
    0.77
    rimination
    0.73
    liction
    0.73
    aliation
    0.73
    usterity
    0.71
    establishment
    0.71
    intel
    0.71
    Activations Density 0.076%

    No Known Activations