© 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. 14642
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of being or existing, particularly in a confident manner

    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
    393
    +0.24
    1.0%
    102
    +0.16
    0.6%
    418
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.24
    0.17
    102
    +0.16
    0.16
    566
    +0.15
    0.13
    Negative Logits
    osate
    -0.96
     residue
    -0.79
     Stability
    -0.77
    Actor
    -0.71
     Which
    -0.69
     Stain
    -0.69
     Must
    -0.69
    rawdownloadcloneembedreportprint
    -0.69
     fallacy
    -0.69
     Explosion
    -0.69
    POSITIVE LOGITS
     able
    1.55
     rewarded
    1.23
     thankful
    1.18
     fooled
    1.16
     forgiven
    1.12
    friends
    1.12
     aware
    1.12
     amazed
    1.08
     tempted
    1.08
     glad
    1.08
    Activations Density 1.371%

    No Known Activations