© 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. 13421
    Prev
    Next
    INDEX
    Explanations

    the word "remind" or variations of it

    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
    389
    +0.15
    0.5%
    679
    +0.15
    0.5%
    641
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    641
    +0.15
    0.04
    665
    +0.15
    0.05
    195
    +0.14
    0.01
    Negative Logits
    estern
    -1.22
    adesh
    -1.15
     ILCS
    -1.07
    abad
    -1.03
    bard
    -0.94
    ccording
    -0.92
    á
    -0.91
    INA
    -0.89
    ר
    -0.86
    EH
    -0.84
    POSITIVE LOGITS
    ingly
    1.63
     Takeru
    1.25
    ĸļ
    1.23
    jas
    1.23
    fulness
    1.20
    isance
    1.11
     vigilance
    1.08
    ening
    1.07
     remind
    1.04
     us
    1.03
    Activations Density 0.967%

    No Known Activations