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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 4720
    Prev
    Next
    INDEX
    Explanations

    references to things being premium quality or related to premium services

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "premium" or high-quality offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.89
    ger
    -0.77
     MacArthur
    -0.75
    gers
    -0.74
    books
    -0.69
    MORE
    -0.64
    nesses
    -0.60
    FUL
    -0.60
     ãĤµ
    -0.58
     paths
    -0.58
    POSITIVE LOGITS
    iership
    1.37
    ature
    1.16
    ortal
    1.10
    iere
    1.07
    ises
    1.05
    merce
    1.04
    iers
    1.04
    inent
    1.00
    inence
    0.98
    arks
    0.97
    Activations Density 0.040%

    No Known Activations