© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6522
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial balance or equilibrium

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.20
    0.6%
    558
    +0.15
    0.5%
    140
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.07
    188
    +0.15
    0.04
    724
    +0.14
    0.05
    Negative Logits
    OLOG
    -1.06
    CHAT
    -1.05
    arij
    -0.96
    iatric
    -0.95
    hood
    -0.91
     ABE
    -0.88
     ink
    -0.88
    obs
    -0.88
    writer
    -0.88
    sil
    -0.88
    POSITIVE LOGITS
     imbalance
    1.28
    amental
    1.26
     balances
    1.18
     balance
    1.18
    balance
    1.17
     balancing
    1.09
     burden
    1.06
    aments
    1.04
    balanced
    1.03
     between
    1.01
    Activations Density 1.101%

    No Known Activations