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. 9879
    Prev
    Next
    INDEX
    Explanations

    words related to loyalty

    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
    63
    +0.11
    0.6%
    8
    +0.08
    0.4%
    152
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.11
    0.02
    63
    +0.08
    0.01
    621
    +0.08
    0.01
    Negative Logits
    externalActionCode
    -0.80
    soDeliveryDate
    -0.68
    ĸļ
    -0.68
     Journals
    -0.65
    Else
    -0.64
     Genetics
    -0.64
     Anthropology
    -0.63
     Seeds
    -0.62
     Jill
    -0.61
    è¦ļéĨĴ
    -0.60
    POSITIVE LOGITS
    ty
    1.04
    ties
    0.82
    thouse
    0.73
    iful
    0.70
    erate
    0.69
     loyal
    0.68
    eties
    0.66
    izations
    0.65
    itionally
    0.65
    elin
    0.65
    Activations Density 0.006%

    No Known Activations