Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5574
    Prev
    Next
    INDEX
    Explanations

    words starting with "uss"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the string "uss" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISA
    -0.72
    cffffcc
    -0.71
     LIFE
    -0.65
    attled
    -0.62
    ISO
    -0.62
     turf
    -0.62
    Steam
    -0.59
    oreal
    -0.58
    bably
    -0.58
    GY
    -0.58
    POSITIVE LOGITS
    engers
    1.16
    alam
    1.02
    olini
    1.02
    enger
    0.99
    enegger
    0.97
    es
    0.96
    ortment
    0.96
    ault
    0.94
    etts
    0.93
    nell
    0.92
    Activations Density 0.019%

    No Known Activations