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. 4-RES-JB
    6. 10009
    Prev
    Next
    INDEX
    Explanations

    references to various types of ropes

    oai_token-act-pair · gpt-3.5-turbo

    references to types of ropes and related materials

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

    No Comments

    Negative Logits
    ropolitan
    -0.82
    apolis
    -0.74
    ansion
    -0.74
    ctuary
    -0.73
    ãĥ´
    -0.73
    hem
    -0.69
    rator
    -0.68
    ensation
    -0.68
    itia
    -0.68
    estine
    -0.68
    POSITIVE LOGITS
     rope
    1.07
     bondage
    0.92
    asso
    0.89
     strap
    0.89
     ropes
    0.87
    pipe
    0.86
     dyed
    0.81
    MpServer
    0.78
    pees
    0.78
     snakes
    0.77
    Activations Density 0.014%

    No Known Activations