© 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. 1689
    Prev
    Next
    INDEX
    Explanations

    words related to computer hardware and technology

    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
    485
    +0.15
    0.5%
    49
    +0.15
    0.5%
    551
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.15
    0.03
    49
    +0.15
    0.03
    485
    +0.14
    0.03
    Negative Logits
    amba
    -1.16
    elsen
    -1.15
     DRAG
    -1.15
    mberg
    -1.10
    ividual
    -1.05
    ppo
    -0.99
    sterdam
    -0.98
    elaide
    -0.97
    minent
    -0.97
    illary
    -0.96
    POSITIVE LOGITS
     than
    1.01
     trivial
    0.98
     unimagin
    0.94
     unpleasant
    0.94
     pricey
    0.92
     conservative
    0.90
     reliably
    0.89
     inconvenient
    0.89
     innocuous
    0.89
     envis
    0.88
    Activations Density 0.317%

    No Known Activations