© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 10650
    Prev
    Next
    INDEX
    Explanations

    terms related to the material "concrete"

    oai_token-act-pair · gpt-3.5-turbo

    the term "concrete" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awar
    -0.96
    tml
    -0.83
    owship
    -0.79
    olulu
    -0.77
    atches
    -0.76
    oresc
    -0.72
    astern
    -0.70
    aving
    -0.68
    rake
    -0.68
    othal
    -0.67
    POSITIVE LOGITS
    crete
    1.22
     concrete
    1.05
     slab
    0.91
     coffin
    0.78
     cement
    0.77
     Jungle
    0.75
     jungle
    0.73
    works
    0.72
     bunker
    0.71
    pain
    0.71
    Activations Density 0.009%

    No Known Activations