© 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. 0-RES-JB
    11. 19920
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "time lapse"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to time-based changes or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     har
    -0.63
     maiden
    -0.63
     standard
    -0.61
     Zoro
    -0.60
     consolation
    -0.60
     disgu
    -0.59
     foreign
    -0.59
     royalties
    -0.59
     pleased
    -0.59
     bod
    -0.58
    POSITIVE LOGITS
    apse
    4.66
    apses
    3.78
    apsed
    2.54
    aps
    1.52
     lapse
    1.18
    ideshow
    1.12
    ateral
    1.12
    aptic
    1.10
    erity
    0.99
    ocaust
    0.98
    Activations Density 0.017%

    No Known Activations