© 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 Local
    5. 6-RES_SCL-AJT
    6. 39491
    Prev
    Next
    INDEX
    Explanations

    empty spaces or things that are vacant

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.20
    0.8%
    288
    +0.14
    0.6%
    726
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.20
    0.18
    362
    +0.14
    0.10
    191
    +0.13
    0.06
    Negative Logits
    abol
    -0.99
    arya
    -0.93
    dar
    -0.86
    ect
    -0.84
    ector
    -0.82
    CVE
    -0.81
    Murray
    -0.80
    Pac
    -0.79
    Downloadha
    -0.79
    ection
    -0.78
    POSITIVE LOGITS
     space
    0.97
     spaces
    0.95
    igue
    0.93
     empty
    0.93
     shells
    0.92
     Empty
    0.91
     calories
    0.90
     bottles
    0.88
     beds
    0.88
     shelves
    0.86
    Activations Density 6.936%

    No Known Activations