© 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. 8-RES-JB
    11. 22514
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for words related to the construction or establishment of physical structures or facilities

    oai_token-act-pair · gpt-3.5-turbo

    references to community infrastructure and development projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.66
     corners
    -0.63
     buttocks
    -0.62
     humidity
    -0.61
    hya
    -0.60
    istered
    -0.60
    76561
    -0.60
     discomfort
    -0.59
    ynes
    -0.59
     extremes
    -0.58
    POSITIVE LOGITS
     staffed
    0.83
     dedicated
    0.76
     modeled
    0.76
     someday
    0.75
    enium
    0.75
     capable
    0.73
     prototype
    0.70
    achment
    0.66
    iphate
    0.66
    oppable
    0.65
    Activations Density 0.480%

    No Known Activations