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

    Neuronpedia

    APICircuit 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 L0 E2E Recon
    5. 2-RES_SLEFR-AJT
    6. 5382
    Prev
    Next
    INDEX
    Explanations

    terms related to carbon and energy production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_slefr-ajt/2-res_slefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.21
    0.9%
    516
    +0.17
    0.7%
    647
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.08
    220
    +0.17
    0.04
    411
    +0.12
    0.05
    Negative Logits
    luaj
    -0.87
    ÅĤ
    -0.84
     Yorkshire
    -0.81
    Äĩ
    -0.78
     Hodg
    -0.78
    hurst
    -0.78
     Beard
    -0.77
    mbuds
    -0.75
    udeb
    -0.74
    ango
    -0.74
    POSITIVE LOGITS
    ogens
    1.11
    ogen
    0.85
     riches
    0.83
     combustion
    0.81
    etic
    0.80
     therapies
    0.79
    ozyg
    0.79
    izations
    0.78
     therap
    0.76
    iously
    0.76
    Activations Density 0.352%

    No Known Activations