Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45217
    Prev
    Next
    INDEX
    Explanations

    phrases related to living conditions and quality of life

    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
    132
    +0.16
    0.7%
    447
    +0.15
    0.6%
    575
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    649
    +0.16
    0.03
    640
    +0.15
    0.18
    479
    +0.14
    0.03
    Negative Logits
    EStream
    -0.98
    reg
    -0.96
    osen
    -0.88
    pport
    -0.83
    eca
    -0.82
    achu
    -0.82
    IFIC
    -0.81
    umen
    -0.77
    ère
    -0.77
    aji
    -0.75
    POSITIVE LOGITS
     Wage
    1.15
    lihood
    1.10
     wage
    0.95
    hart
    0.91
     wills
    0.89
     quarters
    0.88
    ths
    0.84
     liv
    0.81
    living
    0.79
     rooms
    0.79
    Activations Density 8.270%

    No Known Activations