© 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. 32001
    Prev
    Next
    INDEX
    Explanations

    information related to physical locations and entities

    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
    184
    +0.14
    0.6%
    481
    +0.13
    0.6%
    87
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.17
    232
    +0.13
    0.14
    326
    +0.12
    0.24
    Negative Logits
    âĸĵ
    -0.86
    è¦
    -0.78
     corrid
    -0.74
    ãĤ½
    -0.73
     conflic
    -0.72
    ãĥ¼ãĥĨ
    -0.71
    à©
    -0.70
    à¨
    -0.69
     tremend
    -0.69
    ×ŀ
    -0.68
    POSITIVE LOGITS
     âĵĺ
    1.17
     (?,
    0.81
     Remix
    0.75
     LTD
    0.75
    eus
    0.73
     --------------------------------
    0.69
    malink
    0.69
     Scholarship
    0.65
     --------------------
    0.65
    asar
    0.64
    Activations Density 9.813%

    No Known Activations