© 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. 13020
    Prev
    Next
    INDEX
    Explanations

    instances of words related to feelings of pride or self-esteem

    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
    +0.17
    0.8%
    288
    +0.14
    0.7%
    99
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.18
    99
    +0.14
    0.09
    285
    +0.11
    0.05
    Negative Logits
    chnology
    -0.82
    EVA
    -0.66
    pmwiki
    -0.64
    eor
    -0.59
    Phones
    -0.59
    ICA
    -0.58
    alking
    -0.57
     therape
    -0.56
     HELP
    -0.56
    HEAD
    -0.55
    POSITIVE LOGITS
    ful
    1.05
    fulness
    0.97
     pride
    0.95
    fully
    0.90
    FUL
    0.81
    sac
    0.75
    mas
    0.75
    hon
    0.74
    uous
    0.70
    uously
    0.70
    Activations Density 6.339%

    No Known Activations