© 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. 11325
    Prev
    Next
    INDEX
    Explanations

    information related to financial and economic discussions

    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
    183
    +0.17
    0.6%
    25
    +0.17
    0.6%
    331
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.17
    0.05
    762
    +0.17
    0.12
    331
    +0.16
    0.08
    Negative Logits
    atus
    -1.03
    Jump
    -0.92
    ļéĨĴ
    -0.92
    opa
    -0.92
    oggle
    -0.91
    arf
    -0.89
    acas
    -0.88
    psey
    -0.86
     âĢİ
    -0.86
    offer
    -0.84
    POSITIVE LOGITS
     thereof
    1.39
    cffffcc
    1.10
    ?]
    1.07
     alike
    1.06
     versa
    1.05
    !--
    0.98
    ?)
    0.96
     ones
    0.94
    !)
    0.91
     grav
    0.90
    Activations Density 3.874%

    No Known Activations