© 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. 7-RES-JB
    11. 17200
    Prev
    Next
    INDEX
    Explanations

    time-related phrases and temporal sequences

    oai_token-act-pair · gpt-3.5-turbo

    temporal references to actions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ariat
    -0.70
    yout
    -0.65
    wright
    -0.63
    iquid
    -0.61
     2024
    -0.56
     XT
    -0.55
     maker
    -0.54
     IOC
    -0.52
    imble
    -0.51
     Spot
    -0.51
    POSITIVE LOGITS
     mornings
    0.76
     viz
    0.72
    berries
    0.63
    çļĦ
    0.62
    days
    0.61
     outwe
    0.61
     amounted
    0.61
     namely
    0.59
    EStream
    0.58
    tom
    0.57
    Activations Density 0.280%

    No Known Activations