Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34681
    Prev
    Next
    INDEX
    Explanations

    topics related to production and productivity, with a focus on various industries and economic activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.23
    1.0%
    216
    +0.19
    0.9%
    288
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.23
    0.18
    160
    +0.19
    0.18
    274
    +0.14
    0.11
    Negative Logits
    laus
    -0.91
    leans
    -0.82
    olulu
    -0.77
    nee
    -0.75
    cknowled
    -0.75
    eneg
    -0.72
    istani
    -0.69
    igmat
    -0.69
    aiman
    -0.69
     Brow
    -0.65
    POSITIVE LOGITS
     quotas
    0.86
     output
    0.78
     capacities
    0.74
     ministry
    0.74
     capacity
    0.73
     productivity
    0.72
     capability
    0.71
     juices
    0.71
     production
    0.70
     goods
    0.65
    Activations Density 9.485%

    No Known Activations