© 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. 40762
    Prev
    Next
    INDEX
    Explanations

    mentions of news events and political figures

    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
    407
    +0.13
    0.5%
    208
    +0.12
    0.5%
    690
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.13
    0.07
    293
    +0.12
    0.05
    737
    +0.11
    0.06
    Negative Logits
    ĪĴ
    -0.90
    paio
    -0.84
    luster
    -0.80
    ãĤ¹ãĥĪ
    -0.77
    quartered
    -0.76
    conservancy
    -0.74
    senal
    -0.73
     primates
    -0.70
     numbering
    -0.70
    ailability
    -0.69
    POSITIVE LOGITS
    /_
    0.89
    biz
    0.85
    dp
    0.82
    fo
    0.82
    cdn
    0.82
    twitter
    0.81
    nz
    0.78
    legraph
    0.77
    000000
    0.77
    fw
    0.77
    Activations Density 2.870%

    No Known Activations