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. 4-RES-JB
    6. 3482
    Prev
    Next
    INDEX
    Explanations

    words related to individuals or entities with the term "uss" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "uss"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISA
    -0.65
    ISO
    -0.64
    dfx
    -0.64
     LIFE
    -0.63
    cffffcc
    -0.60
     turf
    -0.60
    attled
    -0.60
     GAME
    -0.60
     potency
    -0.59
     ILCS
    -0.58
    POSITIVE LOGITS
    engers
    1.17
    alam
    1.09
    es
    1.04
    enger
    1.03
    olini
    0.97
    etts
    0.97
    enegger
    0.96
    edIn
    0.94
    ault
    0.94
    ures
    0.93
    Activations Density 0.014%

    No Known Activations