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. 21251
    Prev
    Next
    INDEX
    Explanations

    the word "to" with varying strength

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "it’s hard to"

    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
     Conditions
    -0.72
    plates
    -0.68
     embodiments
    -0.66
     Flags
    -0.65
    items
    -0.64
    cand
    -0.60
     Votes
    -0.60
    faces
    -0.59
    Maker
    -0.58
     Sierra
    -0.58
    POSITIVE LOGITS
     imagine
    1.34
     reconcile
    1.30
     quantify
    1.25
     distinguish
    1.22
     justify
    1.20
     convince
    1.17
     conceive
    1.17
     discern
    1.15
     differentiate
    1.14
     compare
    1.13
    Activations Density 0.074%

    No Known Activations