© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32083
    Prev
    Next
    INDEX
    Explanations

    information related to natural disasters and social issues

    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
    +0.35
    1.6%
    378
    +0.10
    0.5%
    691
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.35
    0.07
    705
    +0.10
    0.13
    362
    +0.10
    0.13
    Negative Logits
    anwhile
    -0.68
     Translation
    -0.67
    catentry
    -0.64
     IOC
    -0.59
     momentarily
    -0.58
     horm
    -0.56
     beware
    -0.54
     Seas
    -0.52
     upgr
    -0.51
     Dimension
    -0.51
    POSITIVE LOGITS
     nor
    1.41
     whatsoever
    1.09
     anymore
    1.07
     slightest
    1.02
    nor
    1.02
     anywhere
    0.94
     anybody
    0.88
     either
    0.86
     EVER
    0.84
    ught
    0.81
    Activations Density 21.269%

    No Known Activations