© 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. 4-RES-JB
    11. 10331
    Prev
    Next
    INDEX
    Explanations

    words related to authoritarianism and human rights

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with humanitarian and authoritarian themes

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

    No Comments

    Negative Logits
    VEN
    -0.77
    UX
    -0.77
    enery
    -0.70
     Alloy
    -0.67
    URES
    -0.67
    TD
    -0.66
     Yelp
    -0.66
    touch
    -0.64
    BOOK
    -0.63
    FORMATION
    -0.63
    POSITIVE LOGITS
    ians
    1.17
    itar
    0.98
    iak
    0.92
    ters
    0.90
    iano
    0.89
    inals
    0.89
    tarian
    0.87
    ilateral
    0.87
    iac
    0.86
    ienne
    0.85
    Activations Density 0.012%

    No Known Activations