© 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. 1501
    Prev
    Next
    INDEX
    Explanations

    terms related to aviation and transportation

    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
    +0.12
    0.8%
    89
    +0.09
    0.6%
    527
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.07
    89
    +0.09
    0.04
    575
    +0.08
    0.05
    Negative Logits
    andra
    -0.66
    kai
    -0.65
    ifier
    -0.64
    ifiers
    -0.62
    hips
    -0.59
    20439
    -0.59
    eton
    -0.59
    ividual
    -0.55
    utterstock
    -0.53
    spring
    -0.53
    POSITIVE LOGITS
     Safety
    0.55
     Emirates
    0.52
    Safety
    0.52
     fumes
    0.49
     fraternity
    0.49
     Expend
    0.49
     Ticket
    0.49
     Systems
    0.48
     Standards
    0.47
     Altern
    0.47
    Activations Density 0.285%

    No Known Activations