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. 12019
    Prev
    Next
    INDEX
    Explanations

    dates in the format of month/day/year

    oai_token-act-pair · gpt-3.5-turbo

    components of a date or time format

    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
     grop
    -0.70
    ļéĨĴ
    -0.65
     Dragonbound
    -0.65
     creep
    -0.63
     chop
    -0.63
     effort
    -0.61
     soar
    -0.60
     Daly
    -0.60
     shrink
    -0.60
     orphans
    -0.59
    POSITIVE LOGITS
    2015
    1.16
    2014
    1.15
    2016
    1.13
    2012
    1.13
    2017
    1.13
    31
    1.11
    2013
    1.11
    16
    1.09
    Aug
    1.06
    2018
    1.06
    Activations Density 0.020%

    No Known Activations