© 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. 4621
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and news

    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
    +0.36
    1.8%
    469
    +0.11
    0.6%
    195
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.36
    0.13
    195
    +0.11
    0.01
    469
    +0.11
    0.08
    Negative Logits
    been
    -0.76
     anymore
    -0.68
    heed
    -0.68
    tan
    -0.63
    arta
    -0.63
    venge
    -0.62
    yond
    -0.62
    volent
    -0.58
     Yourself
    -0.58
    magic
    -0.56
    POSITIVE LOGITS
     abruptly
    0.72
    nesday
    0.70
     briefly
    0.69
     tremend
    0.68
     initially
    0.67
     originally
    0.67
     unanimously
    0.66
     last
    0.65
     yesterday
    0.64
     unsuccessfully
    0.63
    Activations Density 15.271%

    No Known Activations