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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 7-RES-JB
    6. 492
    Prev
    Next
    INDEX
    Explanations

    phrases related to duration or time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the passage of time and duration

    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
    ħĭ
    -0.78
    oiler
    -0.76
    irie
    -0.71
    enemy
    -0.71
    idable
    -0.70
    always
    -0.68
    ntil
    -0.67
    lvl
    -0.67
    eus
    -0.66
    tag
    -0.62
    POSITIVE LOGITS
     (~
    0.89
     hiatus
    0.86
     longer
    0.83
     digest
    0.73
     elapsed
    0.72
     gestation
    0.70
     downtime
    0.68
    romy
    0.68
     msec
    0.67
     turnaround
    0.67
    Activations Density 0.067%

    No Known Activations