© 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. 32689
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts

    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
    +0.18
    0.7%
    421
    +0.14
    0.5%
    288
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.18
    0.07
    362
    +0.14
    0.08
    421
    +0.14
    0.07
    Negative Logits
    lain
    -1.03
    poke
    -0.87
    lr
    -0.86
    netflix
    -0.82
     TAMADRA
    -0.81
    wic
    -0.79
    rose
    -0.78
    gger
    -0.78
     Zin
    -0.77
     Nieto
    -0.76
    POSITIVE LOGITS
     transactions
    1.09
     literacy
    1.04
     transaction
    0.97
     advisor
    0.95
    ization
    0.95
     clout
    0.95
     institutions
    0.94
     advisors
    0.94
     adviser
    0.93
     dealings
    0.92
    Activations Density 7.743%

    No Known Activations