© 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 Local
    9. 6-RES_SCL-AJT
    11. 3724
    Prev
    Next
    INDEX
    Explanations

    detailed information about sports events and statistics

    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
    266
    +0.52
    6.6%
    447
    +0.25
    3.2%
    480
    +0.09
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.52
    -0.35
    266
    +0.25
    0.93
    276
    +0.09
    0.33
    Negative Logits
     thereof
    -0.30
     thereto
    -0.28
    }.
    -0.27
    $.
    -0.27
    ]."
    -0.27
    .).
    -0.27
    )."
    -0.25
     respectively
    -0.25
    .''
    -0.24
    .</
    -0.23
    POSITIVE LOGITS
    ¶
    0.22
     Profile
    0.21
    resa
    0.20
     Canaver
    0.20
    undrum
    0.19
     nutshell
    0.18
    ':
    0.18
     disclaimer
    0.18
     âĢº
    0.18
     Edit
    0.18
    Activations Density 96.003%

    No Known Activations