© 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. 13614
    Prev
    Next
    INDEX
    Explanations

    complex sequences of characters that don't follow a typical language pattern

    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
    289
    +0.21
    0.7%
    496
    +0.14
    0.5%
    202
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.21
    0.02
    289
    +0.14
    0.01
    176
    +0.13
    0.02
    Negative Logits
    uberty
    -0.97
    ormal
    -0.96
    apse
    -0.95
    elling
    -0.94
    eral
    -0.94
    eele
    -0.93
    emetery
    -0.93
    estone
    -0.91
    leground
    -0.91
     dominated
    -0.88
    POSITIVE LOGITS
    æ
    1.44
     Uriel
    1.31
    ãĢIJ
    1.26
    åī
    1.26
    ãģĤ
    1.23
    ãĢĮ
    1.22
    æĹ
    1.21
    åIJ
    1.20
    åı
    1.19
    å§
    1.18
    Activations Density 0.119%

    No Known Activations