© 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. 17607
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions that occurred at some point in the past

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "earlier" in various contexts

    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
    hop
    -0.77
    drivers
    -0.69
    alion
    -0.69
    rail
    -0.66
    tre
    -0.62
    rod
    -0.62
    requires
    -0.62
    agra
    -0.62
    HO
    -0.61
    Pros
    -0.61
    POSITIVE LOGITS
    than
    0.84
     than
    0.81
    foundland
    0.81
     versions
    0.78
     generations
    0.76
    oug
    0.69
     editions
    0.69
     iterations
    0.68
     Than
    0.67
    osta
    0.65
    Activations Density 0.017%

    No Known Activations