© 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. 1810
    Prev
    Next
    INDEX
    Explanations

    references to the color green

    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
    459
    +0.23
    0.8%
    269
    +0.17
    0.6%
    70
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.23
    0.05
    525
    +0.17
    0.05
    269
    +0.15
    0.04
    Negative Logits
    gerald
    -1.07
    mble
    -1.00
    nces
    -0.98
    Downloadha
    -0.94
    orically
    -0.93
    ebin
    -0.89
    ̶
    -0.88
     sshd
    -0.87
    staking
    -0.86
     Severus
    -0.83
    POSITIVE LOGITS
    grass
    1.44
    wich
    1.30
    stuff
    1.28
    house
    1.21
    leaf
    1.18
    esis
    1.18
    houses
    1.17
    igans
    1.16
    stone
    1.16
    baum
    1.14
    Activations Density 1.103%

    No Known Activations