© 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. 40723
    Prev
    Next
    INDEX
    Explanations

    references to market-related terms and scenarios

    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
    +0.24
    1.0%
    496
    +0.16
    0.7%
    288
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    561
    +0.24
    0.08
    681
    +0.16
    0.07
    160
    +0.14
    0.12
    Negative Logits
     Drac
    -0.78
    tein
    -0.77
    racuse
    -0.77
    ignt
    -0.75
    arrass
    -0.74
     Fas
    -0.73
     Lak
    -0.73
     Mountains
    -0.72
    ensions
    -0.71
     Banner
    -0.71
    POSITIVE LOGITS
    places
    1.64
    eers
    1.46
    hare
    1.31
    eer
    1.03
    place
    0.98
    eering
    0.90
    ele
    0.89
     prices
    0.88
     markets
    0.87
     share
    0.85
    Activations Density 7.855%

    No Known Activations