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. 3-RES-JB
    6. 8682
    Prev
    Next
    INDEX
    Explanations

    words related to electrical power generation, especially hydroelectric power

    oai_token-act-pair · gpt-3.5-turbo

    terms related to electric power generation and renewable energy sources

    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
     Wilde
    -0.82
     Pupp
    -0.67
    ////////////////////////////////
    -0.66
    Cath
    -0.65
    aro
    -0.63
     Reese
    -0.63
     hairs
    -0.62
    PRES
    -0.62
    bery
    -0.62
    Ub
    -0.61
    POSITIVE LOGITS
     dams
    1.14
     modernization
    0.88
    electric
    0.87
     leasing
    0.86
    mining
    0.86
     dred
    0.85
    ilitation
    0.85
     feasibility
    0.82
    ity
    0.82
     redevelopment
    0.81
    Activations Density 0.030%

    No Known Activations