© 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. 2-RES-JB
    11. 24195
    Prev
    Next
    INDEX
    Explanations

    references to social media handle "@JP", potentially associated with sports or events

    oai_token-act-pair · gpt-3.5-turbo

    references to the entity "JP" or "JPMorgan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rights
    -0.82
     Hurricanes
    -0.79
    leneck
    -0.79
    mberg
    -0.74
    ships
    -0.73
    teenth
    -0.70
    rums
    -0.70
     thirds
    -0.69
     Rebels
    -0.68
    querque
    -0.67
    POSITIVE LOGITS
    JP
    1.36
    EG
    1.04
    KR
    0.95
    NI
    0.91
    oint
    0.89
    IME
    0.87
     JP
    0.86
    PS
    0.85
    ACK
    0.83
    PLIC
    0.82
    Activations Density 0.004%

    No Known Activations