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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 21462
    Prev
    Next
    INDEX
    Explanations

    phrases related to durations of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time periods related to injuries or absences in sports

    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
    glass
    -0.78
    quartered
    -0.72
    sonian
    -0.67
    KK
    -0.64
    âĢķ
    -0.64
     âĨij
    -0.63
    Learn
    -0.61
    cart
    -0.60
    Enlarge
    -0.60
    IQ
    -0.60
    POSITIVE LOGITS
     awhile
    1.05
     eternity
    0.96
     purposes
    0.91
     sake
    0.90
    wards
    0.87
     foreseeable
    0.85
     sure
    0.82
     2018
    0.80
     stretches
    0.78
     reasons
    0.78
    Activations Density 0.177%

    No Known Activations