© 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. 34863
    Prev
    Next
    INDEX
    Explanations

    contractions and colloquial language

    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
    447
    +0.18
    0.7%
    326
    +0.14
    0.6%
    339
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.18
    0.12
    354
    +0.14
    0.12
    551
    +0.13
    0.10
    Negative Logits
    senal
    -0.81
    planet
    -0.74
    cius
    -0.74
    Offline
    -0.72
    CTV
    -0.72
    ourke
    -0.72
    UI
    -0.71
    asse
    -0.70
    topic
    -0.70
    encer
    -0.70
    POSITIVE LOGITS
     gladly
    1.24
     gotta
    1.03
     be
    1.03
     happily
    0.98
     see
    0.98
     probably
    0.96
     never
    0.94
     continue
    0.89
     doubtless
    0.87
     get
    0.87
    Activations Density 8.528%

    No Known Activations