© 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 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. 33547
    Prev
    Next
    INDEX
    Explanations

    references to dice, rolling dice, and outcomes related to dice in various contexts, such as gaming, statistics, and metaphorical use

    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
    +0.14
    0.8%
    326
    +0.10
    0.6%
    420
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.21
    326
    +0.10
    0.20
    698
    +0.08
    0.08
    Negative Logits
    onyms
    -0.56
     Kut
    -0.56
    ajo
    -0.55
    ovie
    -0.55
    ONSORED
    -0.54
    ĺħ
    -0.52
    heses
    -0.52
     Aad
    -0.51
    artney
    -0.51
    ®
    -0.50
    POSITIVE LOGITS
     dice
    0.69
     rolls
    0.63
     pool
    0.60
     roll
    0.57
     Cutter
    0.56
     rolling
    0.56
    pool
    0.56
     pools
    0.54
     balls
    0.53
     crunch
    0.52
    Activations Density 6.415%

    No Known Activations