© 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. 4679
    Prev
    Next
    INDEX
    Explanations

    locations or positions near specific landmarks or in relation to specific 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
    447
    +0.30
    1.7%
    393
    +0.17
    1.0%
    362
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    64
    +0.30
    -0.25
    138
    +0.17
    0.29
    447
    +0.12
    0.32
    Negative Logits
    among
    -0.60
     anew
    -0.59
     according
    -0.57
     msec
    -0.56
     accordingly
    -0.55
    note
    -0.51
    manship
    -0.51
     thereafter
    -0.51
     wisely
    -0.51
     distinguishes
    -0.50
    POSITIVE LOGITS
     periphery
    0.84
     end
    0.84
     horizon
    0.74
     bottom
    0.69
     extremes
    0.68
     sidelines
    0.68
     outskirts
    0.67
    irs
    0.67
     heights
    0.67
     outset
    0.66
    Activations Density 14.828%

    No Known Activations