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. 19668
    Prev
    Next
    INDEX
    Explanations

    the word "beginning"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "at the beginning"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    incinn
    -0.70
    aths
    -0.68
    hemat
    -0.61
    verbs
    -0.60
    OUP
    -0.56
    ternity
    -0.56
    avorite
    -0.56
    dain
    -0.55
     dyed
    -0.54
     sacrific
    -0.53
    POSITIVE LOGITS
     stages
    1.14
     of
    1.04
     thereof
    0.99
     phases
    0.87
    nings
    0.81
     phase
    0.79
    liest
    0.77
     OF
    0.75
    of
    0.75
     stage
    0.75
    Activations Density 0.030%

    No Known Activations