© 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. 10-RES-JB
    11. 24367
    Prev
    Next
    INDEX
    Explanations

    health and news-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news topics, particularly health and general current events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignt
    -0.81
    ersen
    -0.67
    ueless
    -0.64
    aughs
    -0.64
    igi
    -0.64
    owicz
    -0.62
     Forsaken
    -0.62
    inka
    -0.62
    ĸļ
    -0.60
     Antiqu
    -0.59
    POSITIVE LOGITS
    flash
    1.01
    room
    0.97
    letters
    0.93
    rooms
    0.91
    LET
    0.88
    reader
    0.85
    groups
    0.83
    ource
    0.81
     literacy
    0.80
    feed
    0.78
    Activations Density 0.017%

    No Known Activations