© 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. 12964
    Prev
    Next
    INDEX
    Explanations

    keywords related to coding and programming such as functions, variables, and technical terms

    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
    +0.38
    2.0%
    326
    +0.11
    0.6%
    411
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    766
    +0.38
    0.11
    184
    +0.11
    0.05
    375
    +0.09
    0.06
    Negative Logits
    ĸļ
    -0.74
    hra
    -0.63
    ngth
    -0.62
    othal
    -0.60
    osate
    -0.59
    oft
    -0.59
    udence
    -0.58
    emale
    -0.58
    hon
    -0.57
    atic
    -0.57
    POSITIVE LOGITS
     custom
    0.79
     bindings
    0.77
     dependencies
    0.74
     initialization
    0.73
     configuration
    0.71
     configurations
    0.67
     configure
    0.66
     declarations
    0.66
     customized
    0.66
     scripts
    0.65
    Activations Density 15.024%

    No Known Activations