© 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. 1-RES-JB
    11. 7618
    Prev
    Next
    INDEX
    Explanations

    recent events or situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recent events and quantities that indicate growth or inadequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aimon
    -0.85
    anders
    -0.73
    asio
    -0.70
    aden
    -0.62
    ounge
    -0.62
    UGE
    -0.62
     Cohn
    -0.62
    andi
    -0.61
    REL
    -0.61
     reef
    -0.60
    POSITIVE LOGITS
    ly
    2.35
    LY
    1.55
    liness
    1.22
    lys
    1.22
    fully
    1.06
    edly
    1.06
    lies
    1.03
    liest
    1.01
    ELY
    0.97
    nered
    0.92
    Activations Density 0.072%

    No Known Activations