© 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. 10-RES-JB
    11. 9940
    Prev
    Next
    INDEX
    Explanations

    time-sensitive actions or deadlines

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "time."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.70
    insula
    -0.66
    avorite
    -0.63
    ystem
    -0.62
     Dive
    -0.61
    halla
    -0.61
    oret
    -0.60
    riad
    -0.60
    ophy
    -0.60
    iary
    -0.58
    POSITIVE LOGITS
    frames
    1.21
    frame
    0.97
    zone
    0.87
     frame
    0.87
     stamps
    0.84
     zones
    0.83
     intervals
    0.82
     frames
    0.81
     periods
    0.80
    trial
    0.79
    Activations Density 0.043%

    No Known Activations