© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22320
    Prev
    Next
    INDEX
    Explanations

    phrases indicating being the first to know or hear about something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating being the first to know or experience something

    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
     thous
    -0.70
     embodiments
    -0.69
    ĺħ
    -0.63
    GRE
    -0.63
     juggling
    -0.61
     Replacement
    -0.61
    quickShipAvailable
    -0.60
     Temporary
    -0.59
     Powers
    -0.59
     Extension
    -0.58
    POSITIVE LOGITS
     congratulate
    0.96
     admit
    0.90
    itton
    0.82
    edge
    0.81
    ggles
    0.79
     acknowledge
    0.79
    lling
    0.79
    liest
    0.79
     realise
    0.78
    itate
    0.78
    Activations Density 0.078%

    No Known Activations