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. 10-RES-JB
    6. 4180
    Prev
    Next
    INDEX
    Explanations

    phrases related to judgment or assessment

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating time or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •shakespeare
    time for judgement...

    No Comments

    Negative Logits
    LESS
    -0.75
     Defeat
    -0.73
     Archdemon
    -0.71
    FTWARE
    -0.61
     Palest
    -0.59
    NESS
    -0.57
     idi
    -0.56
     oranges
    -0.54
     Rampage
    -0.54
     Atkinson
    -0.53
    POSITIVE LOGITS
    ived
    0.86
    stood
    0.84
    roph
    0.80
    ached
    0.79
     occasion
    0.79
    ev
    0.76
    versely
    0.75
    itud
    0.74
    virt
    0.72
    alien
    0.72
    Activations Density 0.081%

    No Known Activations