© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14582
    Prev
    Next
    INDEX
    Explanations

    commercial-related content, specifically focusing on activities and projects related to commercial enterprises and initiatives

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.26
    1.0%
    459
    +0.19
    0.7%
    167
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.26
    0.07
    365
    +0.19
    0.04
    711
    +0.14
    0.04
    Negative Logits
    arios
    -0.88
    velt
    -0.87
    ktop
    -0.85
    ologies
    -0.85
     Benedict
    -0.81
    hra
    -0.81
    ources
    -0.81
    early
    -0.81
     Recomm
    -0.80
    udic
    -0.80
    POSITIVE LOGITS
    ization
    1.33
    ized
    1.29
     airliner
    1.17
     enterprises
    1.12
    vertising
    1.10
    izing
    1.09
    ised
    1.09
    izes
    1.06
    ity
    1.04
    izations
    1.03
    Activations Density 0.693%

    No Known Activations