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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 3152
    Prev
    Next
    INDEX
    Explanations

    mentions of specific location types within a community, such as restaurants, pubs, pools, factories, stores, parks, or supermarkets

    oai_token-act-pair · gpt-3.5-turbo

    references to locations, particularly places where people gather or interact, such as restaurants, stores, and public areas

    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
     Thing
    -0.64
     hypothesis
    -0.58
    BUG
    -0.57
    ACP
    -0.57
     unification
    -0.56
     dich
    -0.55
     Patriarch
    -0.55
     Initiative
    -0.55
    IDS
    -0.54
    METHOD
    -0.54
    POSITIVE LOGITS
    hips
    1.27
    hops
    1.25
    chool
    1.13
    paces
    1.09
    hip
    1.01
    pring
    1.01
    afety
    1.00
    pace
    0.99
    uggest
    0.96
    ometimes
    0.94
    Activations Density 0.266%

    No Known Activations