© 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. 13946
    Prev
    Next
    INDEX
    Explanations

    words related to cost, savings, and economic factors

    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
    159
    +0.05
    0.5%
    447
    +0.05
    0.5%
    588
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.05
    0.12
    35
    +0.05
    0.07
    381
    +0.04
    0.10
    Negative Logits
    orial
    -0.34
    SPONSORED
    -0.34
    Snow
    -0.34
    acular
    -0.33
    inosaur
    -0.31
     Gleaming
    -0.31
    icus
    -0.30
    ãĤ¨ãĥ«
    -0.30
    north
    -0.29
    umi
    -0.29
    POSITIVE LOGITS
     (<
    0.34
     alternatives
    0.34
     solutions
    0.34
     options
    0.32
     earners
    0.32
     distractions
    0.31
     interventions
    0.31
     ratios
    0.30
     intervals
    0.29
    ensable
    0.29
    Activations Density 14.141%

    No Known Activations