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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35884
    Prev
    Next
    INDEX
    Explanations

    timestamps and locations in news articles

    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
    +0.18
    0.7%
    580
    +0.11
    0.5%
    223
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.18
    0.10
    306
    +0.11
    0.10
    115
    +0.11
    0.09
    Negative Logits
    idious
    -0.87
    atem
    -0.83
    ļéĨĴ
    -0.76
     looph
    -0.73
     hungry
    -0.72
     arrang
    -0.71
     princ
    -0.71
     constitu
    -0.70
    arantine
    -0.70
    essors
    -0.70
    POSITIVE LOGITS
     2017
    1.00
     2018
    0.95
     27
    0.94
     07
    0.93
     2015
    0.92
     04
    0.92
     05
    0.92
    flower
    0.91
     28
    0.91
     29
    0.90
    Activations Density 10.028%

    No Known Activations