© 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. 4845
    Prev
    Next
    INDEX
    Explanations

    studies related to medical conditions and research papers

    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
    +0.19
    0.8%
    238
    +0.12
    0.5%
    326
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.19
    0.21
    6
    +0.12
    0.17
    679
    +0.12
    0.16
    Negative Logits
     millenn
    -0.88
     nodd
    -0.82
     explan
    -0.78
     overrun
    -0.77
     qualitative
    -0.76
     unders
    -0.76
     Leilan
    -0.75
     adjunct
    -0.71
     barg
    -0.71
     invaders
    -0.70
    POSITIVE LOGITS
    Pa
    0.96
    -.
    0.94
    _.
    0.94
    NET
    0.93
    wav
    0.93
    Ħ¢
    0.84
    tif
    0.83
     .
    0.82
    aspx
    0.81
    domain
    0.80
    Activations Density 5.685%

    No Known Activations