© 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. 39727
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "too"

    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
    132
    +0.15
    0.6%
    513
    +0.13
    0.5%
    55
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    744
    +0.15
    0.08
    132
    +0.13
    0.07
    121
    +0.12
    0.08
    Negative Logits
    idia
    -0.77
    inated
    -0.77
    inarily
    -0.76
    seless
    -0.75
    inates
    -0.74
    icipated
    -0.71
    è¦ļéĨĴ
    -0.71
    inatory
    -0.69
    inators
    -0.69
    intel
    -0.69
    POSITIVE LOGITS
    ħĭ
    0.94
    REM
    0.80
     much
    0.79
    oths
    0.77
    ISTORY
    0.75
     Loren
    0.73
    oji
    0.70
     tempting
    0.70
    imei
    0.70
     enthusi
    0.69
    Activations Density 5.188%

    No Known Activations