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. 40276
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events, particularly related to controversy or conflict

    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
    +0.31
    1.5%
    481
    +0.10
    0.5%
    709
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    709
    +0.31
    0.19
    442
    +0.10
    0.12
    708
    +0.10
    0.10
    Negative Logits
     skelet
    -0.60
     PAX
    -0.57
     Citiz
    -0.56
     Prometheus
    -0.55
     antioxid
    -0.54
     entitle
    -0.54
     palate
    -0.53
     Antar
    -0.53
     Amer
    -0.53
     VID
    -0.52
    POSITIVE LOGITS
    ervative
    0.71
    ervatives
    0.70
     Jinping
    0.70
    enei
    0.63
    hler
    0.62
    Äĩ
    0.60
    hedral
    0.60
    vous
    0.60
    tsy
    0.59
    ®
    0.59
    Activations Density 15.656%

    No Known Activations