© 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. 0-RES-JB
    11. 20073
    Prev
    Next
    INDEX
    Explanations

    references to construction-related activities or processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "construction"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ause
    -0.78
    msg
    -0.72
     Saunders
    -0.67
    alert
    -0.67
    otes
    -0.67
     Andromeda
    -0.67
    uds
    -0.65
    iva
    -0.64
    zu
    -0.64
    eu
    -0.64
    POSITIVE LOGITS
     construction
    3.63
     Construction
    2.83
    Construction
    2.64
     constructing
    1.71
     builders
    1.70
     renovation
    1.69
     construct
    1.68
     demolition
    1.60
     constructed
    1.57
     builder
    1.53
    Activations Density 0.023%

    No Known Activations