© 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. 12068
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning and decision-making strategies

    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
    +0.34
    1.1%
    635
    +0.22
    0.7%
    247
    +0.22
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.34
    0.09
    247
    +0.22
    0.06
    575
    +0.22
    0.07
    Negative Logits
    rake
    -1.30
    gur
    -1.22
    vals
    -1.17
    export
    -1.13
    tein
    -1.07
    vol
    -1.03
    pine
    -1.01
    bey
    -0.97
    val
    -0.97
    ibli
    -0.96
    POSITIVE LOGITS
    ategy
    1.30
    ategic
    1.13
    sonian
    1.09
     reversal
    1.06
     strategy
    1.04
    ician
    1.03
    ually
    1.00
     formulation
    0.97
     strategies
    0.97
    riors
    0.97
    Activations Density 1.066%

    No Known Activations