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. 9-RES-JB
    6. 21621
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific duration of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating durations or periods of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Caption
    -0.64
     Athletics
    -0.59
     Anthropology
    -0.59
     Challenges
    -0.59
     Indust
    -0.58
     Mysteries
    -0.58
     Pione
    -0.58
     Engineers
    -0.57
     Rolling
    -0.57
     embassies
    -0.57
    POSITIVE LOGITS
    fold
    1.24
    peat
    1.15
     dimensional
    1.10
    teenth
    1.08
    -
    1.08
    âĢij
    1.02
    some
    1.00
    quel
    1.00
    dimensional
    0.98
    âĢIJ
    0.94
    Activations Density 0.088%

    No Known Activations