© 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. 5935
    Prev
    Next
    INDEX
    Explanations

    words related to high definition 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
    558
    +0.09
    0.5%
    163
    +0.09
    0.5%
    4
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.09
    0.01
    406
    +0.09
    0.01
    326
    +0.09
    0.01
    Negative Logits
     Quan
    -0.62
     Tao
    -0.62
     Pax
    -0.57
     qu
    -0.56
     relay
    -0.55
     void
    -0.55
     Vul
    -0.53
     Void
    -0.53
     Conan
    -0.53
     Phoenix
    -0.52
    POSITIVE LOGITS
    urst
    0.75
    oba
    0.68
    ilion
    0.68
    everal
    0.67
    eda
    0.67
    urat
    0.67
    uly
    0.65
    iverse
    0.63
    hid
    0.62
    irsch
    0.61
    Activations Density 0.043%

    No Known Activations