© 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. 39421
    Prev
    Next
    INDEX
    Explanations

    information related to space technology and medical research

    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
    +0.23
    1.0%
    74
    +0.10
    0.4%
    757
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.23
    0.09
    119
    +0.10
    0.14
    647
    +0.10
    0.08
    Negative Logits
    fell
    -0.86
     Rosenstein
    -0.81
     Tot
    -0.81
     Consent
    -0.80
     graves
    -0.74
     Lynch
    -0.74
     Voices
    -0.73
     Fellowship
    -0.73
     FANTASY
    -0.73
     Torn
    -0.72
    POSITIVE LOGITS
     effic
    1.18
     inexpensive
    1.17
     efficient
    1.16
     additive
    1.15
     versatility
    1.13
     versatile
    1.10
     synerg
    1.08
     efficiently
    1.06
     reusable
    1.05
    efficiency
    1.05
    Activations Density 26.801%

    No Known Activations