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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 39908
    Prev
    Next
    INDEX
    Explanations

    Vietnamese words related to political figures and government entities

    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
    373
    +0.12
    1.1%
    746
    +0.06
    0.5%
    745
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.12
    545
    +0.06
    0.08
    107
    +0.04
    0.05
    Negative Logits
    clair
    -0.36
    Īè
    -0.36
    xus
    -0.36
    ãĤ¯
    -0.36
    ãĥĩãĤ£
    -0.34
    DOS
    -0.33
    hyde
    -0.33
    ãĥĥãĥī
    -0.33
    holes
    -0.33
    ãĤ¦ãĤ¹
    -0.32
    POSITIVE LOGITS
     branch
    0.34
     avenue
    0.30
     Resort
    0.30
    vertis
    0.30
     Mosque
    0.30
     Peninsula
    0.29
     peninsula
    0.29
    \'
    0.28
     arrang
    0.28
     regiment
    0.28
    Activations Density 4.378%

    No Known Activations