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. 20560
    Prev
    Next
    INDEX
    Explanations

    phrases related to research and statistics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the"

    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
    gpu
    -0.72
     beforehand
    -0.70
    --+
    -0.69
    otte
    -0.68
    rade
    -0.68
    Iterator
    -0.65
    æĪ¦
    -0.65
    ointment
    -0.65
    Finish
    -0.65
    join
    -0.65
    POSITIVE LOGITS
     simplest
    1.23
    oret
    1.16
     majority
    1.16
    ories
    1.14
     notion
    1.09
     easiest
    1.08
     earliest
    1.08
     vast
    1.08
     oldest
    1.05
     prevalence
    1.05
    Activations Density 0.595%

    No Known Activations