Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 22332
    Prev
    Next
    INDEX
    Explanations

    time-related terms related to specific durations

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical descriptors related to time and history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laure
    -0.68
     physicists
    -0.66
     regrets
    -0.64
     Yorkers
    -0.62
     brakes
    -0.61
     expresses
    -0.61
     commenters
    -0.59
    rogens
    -0.59
     commenter
    -0.58
    ococ
    -0.58
    POSITIVE LOGITS
    stakes
    0.75
     vicinity
    0.69
     crowded
    0.68
     inaugural
    0.67
    yssey
    0.67
     arena
    0.67
     aftermath
    0.66
    market
    0.66
    opolis
    0.65
    代
    0.65
    Activations Density 0.672%

    No Known Activations