© 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. 14564
    Prev
    Next
    INDEX
    Explanations

    phrases related to Wi-Fi technology

    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
    718
    +0.10
    0.6%
    377
    +0.07
    0.5%
    420
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.10
    0.02
    326
    +0.07
    0.02
    99
    +0.07
    0.02
    Negative Logits
    rics
    -0.56
    otions
    -0.53
    brates
    -0.52
    brate
    -0.50
    ainment
    -0.48
     sway
    -0.48
    Reloaded
    -0.48
     dosage
    -0.48
    aneous
    -0.47
    inate
    -0.47
    POSITIVE LOGITS
    lis
    0.66
    ½
    0.64
    wi
    0.63
    combe
    0.62
    quet
    0.62
    zzle
    0.60
    elsen
    0.56
    quit
    0.55
    ño
    0.54
    urst
    0.54
    Activations Density 0.076%

    No Known Activations