© 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. 13070
    Prev
    Next
    INDEX
    Explanations

    email addresses ending in '@gmail.com'

    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
    455
    +0.12
    0.5%
    566
    +0.12
    0.5%
    128
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.12
    0.10
    326
    +0.12
    0.15
    17
    +0.11
    0.04
    Negative Logits
    BILITIES
    -0.95
    loo
    -0.89
    tips
    -0.87
    GBT
    -0.86
    ulative
    -0.85
    glers
    -0.82
     è£ıç
    -0.81
    ItemImage
    -0.79
    lda
    -0.79
    GY
    -0.79
    POSITIVE LOGITS
    gomery
    1.18
    osaurus
    1.12
    ario
    1.08
    ract
    1.07
    ological
    1.03
    rol
    1.03
    aire
    1.03
    ainment
    1.03
    ribut
    1.02
    ractor
    1.00
    Activations Density 4.991%

    No Known Activations