© 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. 33876
    Prev
    Next
    INDEX
    Explanations

    places and geographical locations in written text

    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
    127
    +0.07
    0.5%
    57
    +0.07
    0.5%
    343
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.07
    0.20
    57
    +0.07
    0.06
    683
    +0.06
    0.06
    Negative Logits
     Dragonbound
    -0.50
    makers
    -0.50
    maker
    -0.47
    served
    -0.43
     IMAGES
    -0.43
    interstitial
    -0.42
    Interstitial
    -0.42
    thro
    -0.40
    SHIP
    -0.40
    study
    -0.39
    POSITIVE LOGITS
    awar
    0.81
    emonic
    0.75
    unia
    0.70
    acular
    0.60
    incinn
    0.55
    umin
    0.54
    iami
    0.52
    aco
    0.52
    oday
    0.52
    adena
    0.51
    Activations Density 7.149%

    No Known Activations