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. 8995
    Prev
    Next
    INDEX
    Explanations

    Serbian-related terms or entities

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the term "Ser," which is likely related to the reference of a specific organization or entity

    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
     Beckham
    -0.65
     understanding
    -0.64
    issance
    -0.64
     Downing
    -0.62
     recogn
    -0.62
     Annotations
    -0.60
     Breaker
    -0.60
     Edited
    -0.59
    è£ħ
    -0.59
    merce
    -0.58
    POSITIVE LOGITS
    geant
    1.35
    rano
    1.26
    otonin
    1.25
    mons
    1.21
    gio
    1.12
    pent
    1.11
    gey
    1.09
    bia
    1.06
    ials
    1.01
    gent
    1.01
    Activations Density 0.033%

    No Known Activations