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. 12912
    Prev
    Next
    INDEX
    Explanations

    names related to transportation or objects that can be pushed or pulled

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "cart."

    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
    ITED
    -0.85
    IDENT
    -0.72
     chancellor
    -0.69
    bek
    -0.64
     pact
    -0.62
     IPM
    -0.61
     Norn
    -0.61
     Triangle
    -0.60
    lihood
    -0.59
    ÏĤ
    -0.58
    POSITIVE LOGITS
    ilage
    1.63
    ographer
    1.45
    esian
    1.37
    wright
    1.30
    ographers
    1.26
    ography
    1.17
    otle
    1.15
    ridges
    1.10
    oons
    1.08
    ograph
    1.06
    Activations Density 0.032%

    No Known Activations