Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 45209
    Prev
    Next
    INDEX
    Explanations

    names of individuals and organizations related to political and military activities in the Middle East, with a specific focus on extremist groups

    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
    +0.15
    0.7%
    57
    +0.12
    0.6%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.15
    0.07
    13
    +0.12
    0.09
    57
    +0.11
    0.04
    Negative Logits
    hips
    -0.80
    xual
    -0.78
    NetMessage
    -0.72
    eries
    -0.69
    Ö¼
    -0.66
     Titanic
    -0.64
    obyl
    -0.63
     Dorothy
    -0.63
    éĹĺ
    -0.61
     Episcopal
    -0.61
    POSITIVE LOGITS
     Dhabi
    1.28
     Bakr
    1.11
    hammad
    0.85
    dullah
    0.82
    querque
    0.80
    rahim
    0.80
    ji
    0.79
     Ali
    0.79
    ghan
    0.78
    aida
    0.78
    Activations Density 8.279%

    No Known Activations