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. 5443
    Prev
    Next
    INDEX
    Explanations

    cooking and food preparation methods

    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
    751
    +0.07
    0.5%
    168
    +0.06
    0.5%
    345
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.07
    0.02
    288
    +0.06
    0.02
    326
    +0.06
    0.01
    Negative Logits
    SpaceEngineers
    -0.50
    archment
    -0.48
     Geneva
    -0.45
     Pru
    -0.43
     Wolver
    -0.43
    ãĥ¯ãĥ³
    -0.43
    \\\\\\\\
    -0.43
     mustard
    -0.43
    aukee
    -0.42
     Princ
    -0.42
    POSITIVE LOGITS
     AUD
    0.42
     humor
    0.42
     OWN
    0.41
    MR
    0.39
     strangely
    0.38
     eb
    0.38
     reproduced
    0.37
     alone
    0.37
     OP
    0.37
    chanted
    0.36
    Activations Density 0.024%

    No Known Activations