© 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. 32100
    Prev
    Next
    INDEX
    Explanations

    phrases related to rewards and contests

    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
    739
    +0.06
    0.5%
    447
    +0.06
    0.5%
    40
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.06
    0.11
    211
    +0.06
    -0.01
    40
    +0.06
    0.09
    Negative Logits
    erity
    -0.41
    erate
    -0.39
    umsy
    -0.38
    noon
    -0.37
    apy
    -0.36
    eph
    -0.36
    luck
    -0.35
    andre
    -0.34
     Dragonbound
    -0.34
     Gon
    -0.34
    POSITIVE LOGITS
    ttes
    0.39
     tiers
    0.38
     goodies
    0.37
    Package
    0.36
     package
    0.36
     items
    0.35
     matrix
    0.34
     pack
    0.34
     packages
    0.34
     packaging
    0.34
    Activations Density 8.918%

    No Known Activations