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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5425
    Prev
    Next
    INDEX
    Explanations

    terms related to educational lectures

    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
    679
    +0.13
    0.7%
    235
    +0.12
    0.7%
    707
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.13
    0.01
    11
    +0.12
    0.01
    354
    +0.09
    0.01
    Negative Logits
    merga
    -0.62
    perm
    -0.59
    earances
    -0.59
    rama
    -0.59
    acea
    -0.58
    itability
    -0.58
    bang
    -0.56
     nesting
    -0.55
    legate
    -0.55
     legalization
    -0.54
    POSITIVE LOGITS
    ĸļ
    0.90
     lecture
    0.75
     Lect
    0.70
     Halls
    0.67
    hemat
    0.67
     lectures
    0.64
    Course
    0.64
    éĥ
    0.64
    ç·
    0.64
    ure
    0.62
    Activations Density 0.013%

    No Known Activations