© 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. 13488
    Prev
    Next
    INDEX
    Explanations

    technical instructions or steps related to setting up and using electronic devices

    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
    690
    +0.13
    0.5%
    274
    +0.13
    0.5%
    694
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.13
    0.06
    526
    +0.13
    -0.01
    78
    +0.12
    0.04
    Negative Logits
    bourg
    -1.04
    enegger
    -0.95
    Cour
    -0.93
    %]
    -0.90
    Filename
    -0.90
    alon
    -0.87
     Shards
    -0.87
    gow
    -0.86
    ivan
    -0.85
    llah
    -0.85
    POSITIVE LOGITS
     standby
    1.06
    screen
    1.06
     mute
    1.03
     automatic
    1.02
     axis
    0.99
     ignition
    0.98
     alarms
    0.97
     blinking
    0.96
     steroids
    0.95
     alarm
    0.94
    Activations Density 1.261%

    No Known Activations