© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 11890
    Prev
    Next
    INDEX
    Explanations

    measurements related to time, such as time periods and time-related data

    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
    504
    +0.15
    0.5%
    641
    +0.14
    0.5%
    251
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.15
    0.08
    504
    +0.14
    0.07
    347
    +0.14
    0.07
    Negative Logits
    ramid
    -1.37
    ortium
    -1.22
    riad
    -1.21
    warts
    -1.10
    ourt
    -1.09
    rosis
    -1.06
    amara
    -1.02
    uthor
    -1.02
    artisan
    -1.02
    erto
    -0.98
    POSITIVE LOGITS
    frames
    1.54
    frame
    1.24
     elapsed
    1.21
    zone
    1.19
     consuming
    1.07
     periods
    1.07
     frame
    1.04
     continuum
    1.03
     period
    1.03
     Spiral
    0.99
    Activations Density 1.400%

    No Known Activations