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 Local
    5. 6-RES_SCL-AJT
    6. 4408
    Prev
    Next
    INDEX
    Explanations

    phrases related to trust and reliance on others

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    +0.21
    1.0%
    288
    +0.12
    0.6%
    283
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    510
    +0.21
    0.10
    150
    +0.12
    0.07
    323
    +0.12
    0.09
    Negative Logits
    pmwiki
    -0.92
    ploy
    -0.85
    ffield
    -0.81
    zz
    -0.76
    ankind
    -0.71
    nesota
    -0.70
    mort
    -0.69
    vention
    -0.69
    cember
    -0.68
    atre
    -0.66
    POSITIVE LOGITS
    worthiness
    1.49
    worthy
    0.90
     trusting
    0.87
    lessly
    0.85
     trust
    0.78
    iliate
    0.76
     trustworthy
    0.75
     confid
    0.73
     trusted
    0.72
     implicitly
    0.71
    Activations Density 6.930%

    No Known Activations