© 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. 17845
    Prev
    Next
    INDEX
    Explanations

    proper names, especially those repeated multiple times

    oai_token-act-pair · gpt-3.5-turbo

    names of people and entities

    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
    road
    -0.69
    door
    -0.68
    gar
    -0.66
    ral
    -0.65
    locked
    -0.65
     treadmill
    -0.65
    spin
    -0.65
    loaded
    -0.64
    stall
    -0.63
    count
    -0.63
    POSITIVE LOGITS
    agne
    0.91
    ENS
    0.89
    éĹĺ
    0.89
    soDeliveryDate
    0.87
    ensen
    0.86
    enstein
    0.85
    \<
    0.81
    enegger
    0.81
    aints
    0.79
    ichick
    0.79
    Activations Density 0.018%

    No Known Activations