© 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. 7-RES-JB
    11. 13496
    Prev
    Next
    INDEX
    Explanations

    references to building materials, specifically bricks and mortar

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "brick" and "mortar" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relativity
    -0.79
    uthor
    -0.71
    ktop
    -0.69
     Voters
    -0.66
    ffect
    -0.66
    aeda
    -0.65
    ivia
    -0.64
    egal
    -0.63
    orescence
    -0.63
    judicial
    -0.63
    POSITIVE LOGITS
    bats
    1.25
    layer
    1.05
    mort
    1.01
    buster
    0.96
    yard
    0.96
    works
    0.92
    busters
    0.90
    shaw
    0.89
    strap
    0.86
     mortar
    0.85
    Activations Density 0.027%

    No Known Activations