© 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. 2-RES-JB
    11. 9124
    Prev
    Next
    INDEX
    Explanations

    numbers related to prices or quantities

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and references to financial transactions

    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
    abol
    -0.90
    kell
    -0.89
    bid
    -0.89
    unal
    -0.81
    pron
    -0.80
    rian
    -0.80
    idi
    -0.79
    unct
    -0.78
    eworld
    -0.77
    idy
    -0.77
    POSITIVE LOGITS
     MHz
    1.05
    Hz
    1.04
     Hz
    0.93
    MHz
    0.88
    0002
    0.86
     Minutes
    0.85
    300
    0.83
    OPLE
    0.83
    400
    0.81
    800
    0.81
    Activations Density 0.019%

    No Known Activations