© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 4768
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and numerical analysis

    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
    +0.22
    1.0%
    680
    +0.12
    0.6%
    340
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.22
    0.39
    255
    +0.12
    0.13
    393
    +0.09
    0.42
    Negative Logits
    mods
    -0.80
    Activ
    -0.75
    Fight
    -0.73
    Cong
    -0.71
     Revival
    -0.69
     [+
    -0.68
    lord
    -0.67
     Rez
    -0.67
    FLAG
    -0.66
    Rated
    -0.66
    POSITIVE LOGITS
     statistical
    1.40
     data
    1.18
     spreadsheet
    1.17
     database
    1.15
     analytics
    1.14
    gorithm
    1.14
     dataset
    1.13
     databases
    1.10
     extrap
    1.09
    analy
    1.09
    Activations Density 34.350%

    No Known Activations