© 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. 12369
    Prev
    Next
    INDEX
    Explanations

    phrases related to journalism and funding requests

    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
    732
    +0.15
    0.6%
    1
    +0.13
    0.5%
    646
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.15
    0.02
    567
    +0.13
    0.02
    733
    +0.12
    0.01
    Negative Logits
    ono
    -1.28
    pee
    -0.99
    illes
    -0.99
    axter
    -0.94
    ajor
    -0.92
    alog
    -0.85
    yang
    -0.85
    BIP
    -0.84
    edi
    -0.84
    anu
    -0.82
    POSITIVE LOGITS
     certs
    0.89
     Gutenberg
    0.79
     assurances
    0.78
     entertain
    0.77
     domains
    0.76
     anticip
    0.74
     amidst
    0.73
     embed
    0.73
     domain
    0.73
     submissions
    0.72
    Activations Density 0.144%

    No Known Activations