© 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 EvalsExportsinterp-engineNEWAPI 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. 7618
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and complex acronyms

    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
    691
    +0.07
    0.5%
    161
    +0.07
    0.5%
    469
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.07
    0.01
    706
    +0.07
    0.01
    373
    +0.07
    -0.00
    Negative Logits
    £ı
    -0.51
    ELF
    -0.47
    ãĥķãĤ©
    -0.47
    Subject
    -0.47
    mson
    -0.46
    PROV
    -0.45
    CVE
    -0.44
    inventoryQuantity
    -0.43
     warr
    -0.42
    ibrary
    -0.42
    POSITIVE LOGITS
    atial
    0.50
    ificial
    0.48
    fman
    0.46
    venient
    0.45
    illet
    0.45
    esville
    0.42
    illes
    0.42
    asso
    0.42
    ishes
    0.41
    agher
    0.41
    Activations Density 0.004%

    No Known Activations