© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35896
    Prev
    Next
    INDEX
    Explanations

    phrases related to abilities or capabilities

    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
    68
    +0.07
    0.5%
    311
    +0.06
    0.4%
    490
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    533
    +0.07
    0.08
    638
    +0.06
    0.05
    763
    +0.06
    0.07
    Negative Logits
     sprinkled
    -0.40
     Directions
    -0.39
    articles
    -0.39
    igl
    -0.37
    uggest
    -0.37
     Neuroscience
    -0.37
     Sham
    -0.37
     Actor
    -0.36
     Ammo
    -0.36
    HEAD
    -0.36
    POSITIVE LOGITS
    osaurus
    0.51
    bos
    0.50
    ioned
    0.49
     anymore
    0.48
     compe
    0.47
    ascript
    0.45
    URES
    0.43
    èª
    0.42
    ribly
    0.42
     Pradesh
    0.42
    Activations Density 7.192%

    No Known Activations