© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3344
    Prev
    Next
    INDEX
    Explanations

    financial and political terms and contexts

    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
    640
    +0.41
    1.5%
    447
    +0.19
    0.7%
    664
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.41
    0.20
    6
    +0.19
    0.12
    373
    +0.14
    -0.08
    Negative Logits
    hement
    -1.08
     destro
    -0.99
     awa
    -0.94
    ngth
    -0.93
     princ
    -0.92
     appe
    -0.89
    ensibly
    -0.87
    ration
    -0.87
     agre
    -0.85
    ardless
    -0.84
    POSITIVE LOGITS
     Emer
    1.04
     âĵĺ
    0.92
    ;;;;;;;;
    0.92
    ;;;;
    0.91
     Lens
    0.89
     Nile
    0.88
    DX
    0.88
     اÙĦ
    0.87
     Moroc
    0.85
    Lens
    0.85
    Activations Density 2.470%

    No Known Activations