© 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. 17733
    Prev
    Next
    INDEX
    Explanations

    word related to pumping such as "pump", "pumping", or "pumps"

    oai_token-act-pair · gpt-3.5-turbo

    references to pumps and pumping activities

    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
    ########
    -0.78
    lihood
    -0.77
    feat
    -0.69
    ------------------------
    -0.68
     Bei
    -0.68
    jar
    -0.66
    nam
    -0.66
    zan
    -0.65
    sm
    -0.64
    wealth
    -0.64
    POSITIVE LOGITS
     pump
    1.18
     pumping
    1.13
    ulic
    1.10
     pumps
    1.03
     Pump
    0.99
     pedal
    0.93
    oline
    0.87
     pumped
    0.83
    cffff
    0.79
    kins
    0.79
    Activations Density 0.012%

    No Known Activations