© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3220
    Prev
    Next
    INDEX
    Explanations

    CNN news articles

    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%
    346
    +0.18
    0.6%
    208
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.21
    0.07
    343
    +0.18
    0.07
    288
    +0.16
    0.08
    Negative Logits
    vol
    -1.07
    hot
    -1.05
    vals
    -1.04
    ven
    -1.04
    phant
    -1.02
    ocene
    -1.01
    plates
    -1.00
    hem
    -0.98
    xual
    -0.95
    hens
    -0.93
    POSITIVE LOGITS
    Money
    1.66
    NOW
    1.28
     affiliate
    1.22
    ILLE
    1.18
    IB
    1.15
    IVERS
    1.10
    icates
    1.09
    ileaks
    1.09
    ienne
    1.09
    igel
    1.07
    Activations Density 0.859%

    No Known Activations