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. 5415
    Prev
    Next
    INDEX
    Explanations

    references to the term "Crystal" in various contexts

    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
    274
    +0.15
    0.6%
    353
    +0.13
    0.5%
    385
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.06
    326
    +0.13
    0.04
    353
    +0.12
    0.04
    Negative Logits
    ologies
    -0.93
    FFFF
    -0.88
    upon
    -0.88
    times
    -0.87
    arsity
    -0.82
    ore
    -0.79
    abol
    -0.78
    esm
    -0.77
    hel
    -0.77
    omp
    -0.76
    POSITIVE LOGITS
     Mason
    0.83
     marker
    0.83
    ignty
    0.81
     markers
    0.79
     Templar
    0.78
    ulic
    0.76
     distilled
    0.72
     crystall
    0.71
     conception
    0.71
     jars
    0.71
    Activations Density 0.215%

    No Known Activations