© 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. 1753
    Prev
    Next
    INDEX
    Explanations

    countries or places

    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
    578
    +0.07
    0.5%
    72
    +0.07
    0.5%
    345
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.07
    0.03
    288
    +0.07
    0.03
    241
    +0.06
    0.01
    Negative Logits
     Carnage
    -0.49
    leaf
    -0.48
    mie
    -0.47
    cards
    -0.43
    bre
    -0.43
    ples
    -0.43
    bell
    -0.43
    lda
    -0.42
    nery
    -0.41
    istries
    -0.41
    POSITIVE LOGITS
    ongs
    0.53
    ULTS
    0.48
    OPLE
    0.46
     unpop
    0.45
     Mehran
    0.43
    INE
    0.43
     Emir
    0.43
    ORTS
    0.43
    =-=-
    0.43
    Downloadha
    0.42
    Activations Density 0.112%

    No Known Activations