© 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 Local
    5. 6-RES_SCL-AJT
    6. 14203
    Prev
    Next
    INDEX
    Explanations

    words related to construction and infrastructure

    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
    +0.21
    1.2%
    481
    +0.14
    0.8%
    744
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.35
    225
    +0.14
    0.18
    575
    +0.09
    0.24
    Negative Logits
    oidal
    -0.59
    ãĤ¿
    -0.52
    icable
    -0.49
    utsche
    -0.49
    FH
    -0.48
     GAM
    -0.47
    £ı
    -0.47
     Gaming
    -0.46
    ibur
    -0.46
    Cart
    -0.45
    POSITIVE LOGITS
    vertisements
    0.57
     Nationwide
    0.52
     nationwide
    0.51
    dates
    0.49
    flush
    0.49
     bleed
    0.48
    onomy
    0.47
    etting
    0.47
     firsthand
    0.47
    nels
    0.47
    Activations Density 15.568%

    No Known Activations