© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 35264
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names and technical terms

    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
    289
    +0.14
    0.6%
    420
    +0.14
    0.6%
    213
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.10
    48
    +0.14
    0.08
    649
    +0.11
    0.04
    Negative Logits
     Clement
    -0.81
    enhagen
    -0.81
    éĹĺ
    -0.81
    yrinth
    -0.80
    xual
    -0.70
     referen
    -0.69
    atories
    -0.68
    aries
    -0.66
    xtap
    -0.65
    aution
    -0.65
    POSITIVE LOGITS
    lehem
    1.60
    iop
    1.30
    amphetamine
    1.30
    ulhu
    1.20
    anol
    1.17
    icone
    1.09
    ylene
    1.08
    yll
    1.06
    omet
    1.02
    ought
    1.01
    Activations Density 5.394%

    No Known Activations