© 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 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. 33456
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and terms related to computations and data analysis

    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
    +0.29
    1.5%
    393
    +0.21
    1.1%
    566
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.29
    0.24
    102
    +0.21
    0.23
    566
    +0.12
    0.18
    Negative Logits
    inav
    -0.79
     congr
    -0.60
    oice
    -0.59
     IMAGES
    -0.59
    onso
    -0.56
    tackle
    -0.56
    edin
    -0.56
    things
    -0.55
     bothers
    -0.55
     scares
    -0.54
    POSITIVE LOGITS
     treated
    0.91
     assumed
    0.89
     considered
    0.89
     shown
    0.89
     hereby
    0.86
     presumed
    0.84
     derived
    0.83
     represented
    0.83
     effected
    0.83
     dependent
    0.82
    Activations Density 9.598%

    No Known Activations