© 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. 11272
    Prev
    Next
    INDEX
    Explanations

    political announcements and updates

    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
    288
    +0.21
    0.7%
    274
    +0.16
    0.6%
    101
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.21
    0.05
    101
    +0.16
    0.07
    274
    +0.15
    0.05
    Negative Logits
    avery
    -1.04
    osph
    -1.01
    imeo
    -0.98
    onz
    -0.97
    isma
    -0.94
    iking
    -0.94
    phe
    -0.91
    obos
    -0.90
    aque
    -0.90
    oil
    -0.90
    POSITIVE LOGITS
     announces
    1.06
     partnerships
    1.05
     publicly
    1.01
    doms
    0.97
    details
    0.96
    quished
    0.95
     beforehand
    0.94
    daq
    0.94
     announcements
    0.90
     waivers
    0.90
    Activations Density 0.840%

    No Known Activations