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. 9-RES-JB
    6. 15119
    Prev
    Next
    INDEX
    Explanations

    places located along riverbanks

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and their relation to bodies of water

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chool
    -0.74
    boxing
    -0.69
    makers
    -0.68
    lance
    -0.66
    Parents
    -0.65
     upbringing
    -0.65
    orsche
    -0.65
    OWN
    -0.65
     audits
    -0.63
     inherit
    -0.63
    POSITIVE LOGITS
     river
    1.30
     creek
    1.20
     Highway
    1.18
     highway
    1.11
     River
    1.07
     Interstate
    1.03
     rivers
    1.02
     Canal
    0.98
     canal
    0.98
     highways
    0.98
    Activations Density 0.206%

    No Known Activations