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. 13835
    Prev
    Next
    INDEX
    Explanations

    financial and technical terms of online transactions

    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
    447
    +0.22
    0.7%
    512
    +0.14
    0.4%
    554
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.22
    0.03
    704
    +0.14
    0.02
    74
    +0.13
    0.03
    Negative Logits
    Ĥª
    -1.22
    agall
    -1.20
    paio
    -1.17
    espie
    -1.05
    ament
    -1.05
    izz
    -1.04
     millenn
    -1.04
    igree
    -1.02
    edIn
    -1.01
    tnc
    -1.00
    POSITIVE LOGITS
    terday
    0.96
    unknown
    0.93
     Prot
    0.91
     [+
    0.89
    iquid
    0.87
    without
    0.87
     absence
    0.85
     passively
    0.82
     Superior
    0.81
    half
    0.81
    Activations Density 0.270%

    No Known Activations