© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3249
    Prev
    Next
    INDEX
    Explanations

    concrete-related words and phrases, such as building materials and structures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.15
    0.5%
    99
    +0.15
    0.5%
    739
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.12
    326
    +0.15
    0.08
    99
    +0.13
    0.07
    Negative Logits
    othal
    -1.10
    awar
    -1.07
    atches
    -1.04
    arak
    -0.96
    cffffcc
    -0.94
    nir
    -0.93
    owship
    -0.91
    oresc
    -0.90
    finder
    -0.89
    uten
    -0.88
    POSITIVE LOGITS
     slab
    1.22
    crete
    1.11
     concrete
    0.98
     blocks
    0.96
    bats
    0.96
     mixer
    0.95
    works
    0.91
     pavement
    0.89
     pave
    0.87
     cement
    0.86
    Activations Density 1.310%

    No Known Activations