Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 7770
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and military topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anarchism, terrorism, and militarization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.77
     DRAG
    -0.73
     Nile
    -0.64
     Thor
    -0.61
     Caesar
    -0.61
     Isles
    -0.61
     Tune
    -0.60
     PAY
    -0.59
     bye
    -0.59
     OW
    -0.57
    POSITIVE LOGITS
    ists
    2.15
    ist
    1.98
    istically
    1.83
    istic
    1.83
    ism
    1.71
    istical
    1.62
    istics
    1.41
    ical
    1.40
    icals
    1.39
    isms
    1.34
    Activations Density 0.101%

    No Known Activations