© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33531
    Prev
    Next
    INDEX
    Explanations

    mentions related to Israeli settlements and peace efforts in the context of Israeli-Palestinian relations

    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
    202
    +0.10
    0.5%
    288
    +0.08
    0.4%
    62
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.25
    125
    +0.08
    0.07
    516
    +0.08
    0.06
    Negative Logits
    Sym
    -0.93
    Phys
    -0.84
    Pitt
    -0.80
    apache
    -0.75
    rious
    -0.71
    Scient
    -0.69
    Scot
    -0.69
    Alert
    -0.69
    OTAL
    -0.68
    Heart
    -0.68
    POSITIVE LOGITS
     sett
    0.83
     Cheong
    0.79
     annexed
    0.79
     genocide
    0.77
     annex
    0.77
     demolished
    0.72
    heid
    0.72
     coerc
    0.69
     bloc
    0.68
     leveled
    0.68
    Activations Density 9.314%

    No Known Activations