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

    Neuronpedia

    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. 4928
    Prev
    Next
    INDEX
    Explanations

    names of political figures and related phrases

    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
    679
    +0.14
    0.7%
    726
    +0.12
    0.6%
    587
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.14
    0.10
    201
    +0.12
    0.07
    709
    +0.11
    0.10
    Negative Logits
    falls
    -0.71
    birth
    -0.68
    points
    -0.67
    enic
    -0.67
    psc
    -0.66
    proof
    -0.66
    estones
    -0.66
    hair
    -0.65
    BAT
    -0.65
    found
    -0.64
    POSITIVE LOGITS
     Erdogan
    1.20
     Tayyip
    1.16
     Erd
    1.04
     Recep
    0.88
    eki
    0.73
    archy
    0.72
    vironment
    0.72
    eering
    0.72
    ovich
    0.71
     Sheikh
    0.71
    Activations Density 8.329%

    No Known Activations