© 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. 34976
    Prev
    Next
    INDEX
    Explanations

    phrases expressing certainty or confidence

    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%
    183
    +0.17
    0.6%
    376
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.18
    0.08
    376
    +0.17
    0.06
    428
    +0.16
    0.06
    Negative Logits
    illin
    -0.88
    gypt
    -0.86
    bian
    -0.83
     compr
    -0.78
    eki
    -0.77
    dra
    -0.77
     cultivating
    -0.76
    Adv
    -0.72
     constrained
    -0.71
    OTOS
    -0.70
    POSITIVE LOGITS
    't
    1.56
    itive
    1.21
    now
    1.11
    geon
    0.99
    cest
    0.97
    stall
    0.95
    nings
    0.95
    etsk
    0.92
    ims
    0.90
    ky
    0.89
    Activations Density 6.839%

    No Known Activations