© 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. 32803
    Prev
    Next
    INDEX
    Explanations

    phrases related to food preparation, specifically steaming

    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
    167
    +0.08
    0.6%
    566
    +0.08
    0.5%
    755
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.08
    0.20
    442
    +0.08
    0.14
    640
    +0.07
    0.26
    Negative Logits
    ei
    -0.49
    xus
    -0.46
     Finder
    -0.45
     Entity
    -0.44
     sovere
    -0.44
    etheless
    -0.43
     Palestin
    -0.43
    liga
    -0.43
    Page
    -0.43
     Leban
    -0.42
    POSITIVE LOGITS
    boat
    0.63
    boats
    0.60
    ampunk
    0.58
     locom
    0.56
    SourceFile
    0.55
    amed
    0.54
    aring
    0.50
    whe
    0.50
    shaw
    0.49
    leted
    0.49
    Activations Density 9.690%

    No Known Activations