© 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. 251
    Prev
    Next
    INDEX
    Explanations

    titanium-related terms and its varying forms

    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
    587
    +0.05
    0.6%
    736
    +0.04
    0.5%
    534
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.05
    0.04
    699
    +0.04
    0.01
    397
    +0.04
    0.02
    Negative Logits
    gage
    -0.33
    ingly
    -0.27
    croft
    -0.26
    baugh
    -0.26
    byter
    -0.25
    fully
    -0.25
    mons
    -0.24
    EStreamFrame
    -0.24
     plur
    -0.24
    riet
    -0.24
    POSITIVE LOGITS
    ensis
    0.32
    odon
    0.29
    ickets
    0.28
     dioxide
    0.28
    zhen
    0.27
    osaurs
    0.27
    aques
    0.27
    icum
    0.26
    ciating
    0.26
     titanium
    0.25
    Activations Density 0.321%

    No Known Activations