© 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 Local
    9. 6-RES_SCL-AJT
    11. 33941
    Prev
    Next
    INDEX
    Explanations

    specific names and proper nouns related to politics, media, and academia

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    421
    +0.09
    0.5%
    316
    +0.08
    0.5%
    644
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.09
    0.11
    599
    +0.08
    0.07
    353
    +0.08
    0.06
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    mble
    -0.69
    xual
    -0.66
    ITNESS
    -0.56
     thumbnail
    -0.54
    è¦ļéĨĴ
    -0.52
     conclud
    -0.51
    ngth
    -0.50
    nesday
    -0.48
    vironment
    -0.48
    POSITIVE LOGITS
    unit
    0.75
    otte
    0.67
    ued
    0.64
    bard
    0.64
     Lag
    0.64
    otle
    0.64
    ueless
    0.63
    ophe
    0.60
    esian
    0.59
    het
    0.58
    Activations Density 12.521%

    No Known Activations