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. 2-RES-JB
    6. 2349
    Prev
    Next
    INDEX
    Explanations

    words related to the material "cement"

    oai_token-act-pair · gpt-3.5-turbo

    uses and references to cement as a material

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    finder
    -0.79
     nerv
    -0.70
    lihood
    -0.69
    arenthood
    -0.66
    option
    -0.65
    yright
    -0.63
    RESULTS
    -0.61
    TH
    -0.61
     Peninsula
    -0.60
    izons
    -0.59
    POSITIVE LOGITS
     cement
    1.36
     mixer
    0.79
    urated
    0.75
     seal
    0.75
     plaster
    0.75
     resin
    0.71
     lime
    0.70
     phosphate
    0.70
    ilings
    0.68
     concrete
    0.68
    Activations Density 0.009%

    No Known Activations