© 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. 32606
    Prev
    Next
    INDEX
    Explanations

    places or locations related to a specific city, such as San Francisco and San Diego

    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
    195
    +0.16
    0.6%
    447
    +0.14
    0.6%
    421
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    746
    +0.16
    0.04
    667
    +0.14
    0.06
    167
    +0.12
    -0.02
    Negative Logits
    llor
    -0.87
    theless
    -0.84
    ilater
    -0.81
    ï¸ı
    -0.79
    xual
    -0.78
    llers
    -0.77
     confir
    -0.72
    anwhile
    -0.72
    ļéĨĴ
    -0.71
     homework
    -0.71
    POSITIVE LOGITS
    San
    1.30
     Francisco
    1.25
     Diego
    1.18
    ctuary
    1.16
     Antonio
    1.11
    gha
    1.06
    ibel
    1.06
    ction
    1.03
    Disk
    1.03
    itary
    1.01
    Activations Density 7.560%

    No Known Activations