© 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. 1769
    Prev
    Next
    INDEX
    Explanations

    information related to 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
    393
    +0.39
    1.5%
    385
    +0.15
    0.6%
    36
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.39
    0.20
    393
    +0.15
    0.19
    385
    +0.15
    0.20
    Negative Logits
    terday
    -0.85
    Bloomberg
    -0.83
     aloud
    -0.76
    Lago
    -0.73
    ADA
    -0.73
    claw
    -0.71
    ettings
    -0.70
    gat
    -0.70
    ãĥĺ
    -0.69
    Privacy
    -0.69
    POSITIVE LOGITS
     same
    1.13
     latest
    1.13
    ses
    1.10
     easiest
    1.05
    same
    1.04
     idea
    1.04
     hardest
    1.03
    ologically
    1.00
     rest
    0.98
     widest
    0.97
    Activations Density 2.612%

    No Known Activations