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

    Neuronpedia

    APICircuit 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. 18407
    Prev
    Next
    INDEX
    Explanations

    phrases related to time duration and activities over extended periods

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, particularly focusing on days, nights, and seasons

    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
    erest
    -0.67
    env
    -0.64
    ename
    -0.63
    Directory
    -0.61
    edia
    -0.61
    enburg
    -0.60
    rics
    -0.60
    ansen
    -0.60
    ahime
    -0.59
    orb
    -0.59
    POSITIVE LOGITS
     LONG
    1.09
    long
    0.98
    orrow
    0.87
     long
    0.85
    days
    0.81
     sqor
    0.78
    night
    0.74
     Long
    0.73
     ago
    0.71
    ciating
    0.71
    Activations Density 0.044%

    No Known Activations