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 CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14022
    Prev
    Next
    INDEX
    Explanations

    phrases related to the sports team name "Chetahs" and "Cheese Puffs"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    526
    +0.14
    0.5%
    162
    +0.13
    0.4%
    420
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.05
    67
    +0.13
    0.05
    420
    +0.13
    0.04
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -1.03
     CTR
    -1.02
    ELF
    -1.01
     Archdemon
    -0.94
    DragonMagazine
    -0.92
    DEF
    -0.90
    ãĥ¼ãĥĨ
    -0.90
     aquarium
    -0.85
     unauthorized
    -0.85
     Anonymous
    -0.84
    POSITIVE LOGITS
    bones
    1.50
    hou
    1.38
    apeake
    1.36
    anut
    1.34
    lean
    1.29
    chet
    1.27
    bag
    1.24
    arest
    1.24
    bags
    1.23
    rolled
    1.21
    Activations Density 0.972%

    No Known Activations