© 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14491
    Prev
    Next
    INDEX
    Explanations

    words related to news articles and updates, particularly when it comes to political news

    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
    201
    +0.12
    0.5%
    230
    +0.11
    0.5%
    182
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.12
    0.02
    182
    +0.11
    0.02
    245
    +0.11
    0.02
    Negative Logits
    kef
    -0.78
    ono
    -0.76
    nai
    -0.76
    tif
    -0.75
    EG
    -0.74
    andom
    -0.72
    ggle
    -0.72
     misunder
    -0.71
    ouses
    -0.70
    gee
    -0.69
    POSITIVE LOGITS
    luaj
    0.84
    currency
    0.80
     Transcript
    0.79
    ilded
    0.79
    notations
    0.77
    bleacher
    0.76
     sourced
    0.75
    ylon
    0.71
    DragonMagazine
    0.70
     transcript
    0.69
    Activations Density 0.068%

    No Known Activations