© 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
    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. 14662
    Prev
    Next
    INDEX
    Explanations

    Twitter hashtags related to specific events or topics

    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
    250
    +0.15
    0.6%
    631
    +0.12
    0.5%
    569
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.15
    0.01
    321
    +0.12
    0.01
    486
    +0.12
    0.01
    Negative Logits
     imperson
    -0.89
     sheds
    -0.87
     flies
    -0.86
     pse
    -0.85
     jars
    -0.82
     Granger
    -0.80
     stacks
    -0.78
     proofs
    -0.77
     likeness
    -0.76
     tunnels
    -0.76
    POSITIVE LOGITS
    Bon
    0.91
    eering
    0.89
    Standard
    0.89
    sg
    0.88
    Traditional
    0.87
    utm
    0.86
    OWN
    0.84
    KT
    0.83
    gp
    0.82
     ?)
    0.82
    Activations Density 0.028%

    No Known Activations