© 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. 40613
    Prev
    Next
    INDEX
    Explanations

    information related to road closures and infrastructure projects in a specific geographic area

    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
    +0.16
    0.8%
    232
    +0.11
    0.5%
    249
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.16
    0.23
    659
    +0.11
    0.20
    145
    +0.10
    0.13
    Negative Logits
     realised
    -0.81
     learnt
    -0.77
     analysed
    -0.76
     apologise
    -0.75
     interrog
    -0.75
     ana
    -0.75
     organising
    -0.73
     diarr
    -0.72
     mate
    -0.72
     bombard
    -0.72
    POSITIVE LOGITS
     Creek
    1.23
     Avenue
    1.11
     Grove
    1.10
     Boulevard
    1.10
    mont
    1.06
     Lakes
    1.04
    vale
    1.04
    ville
    1.04
     Beach
    1.03
     Valley
    1.03
    Activations Density 14.980%

    No Known Activations