© 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. 40785
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming

    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
    314
    +0.13
    0.6%
    48
    +0.10
    0.5%
    615
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    -0.01
    652
    +0.10
    0.10
    365
    +0.10
    0.06
    Negative Logits
     HIP
    -0.77
     Immunity
    -0.77
     Tone
    -0.76
     Knot
    -0.73
     Kills
    -0.70
     ANG
    -0.70
     Companion
    -0.68
     Grounds
    -0.66
     Reborn
    -0.66
     Akin
    -0.65
    POSITIVE LOGITS
    ruction
    1.39
    ition
    1.20
    uments
    1.15
    yright
    1.15
    acters
    1.14
    perature
    1.08
    rolet
    1.05
    unte
    1.04
    alog
    1.04
    artment
    1.03
    Activations Density 6.732%

    No Known Activations