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. 8-RES-JB
    6. 15238
    Prev
    Next
    INDEX
    Explanations

    numerical values related to age and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numeric representations related to age and time intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥķãĤ©
    -0.86
    raq
    -0.79
    Pal
    -0.76
    Tor
    -0.73
     Pul
    -0.71
     Scor
    -0.71
     Pizza
    -0.70
    press
    -0.70
    Cu
    -0.70
     Slime
    -0.70
    POSITIVE LOGITS
     year
    1.24
    Year
    1.21
     YEAR
    1.20
     years
    1.15
    year
    1.11
     Year
    1.03
     Years
    1.03
     decade
    1.02
    years
    0.98
     yr
    0.91
    Activations Density 0.195%

    No Known Activations