© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 35108
    Prev
    Next
    INDEX
    Explanations

    terms related to looting, loot boxes, and various associated actions and items

    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
    +0.20
    0.9%
    288
    +0.13
    0.6%
    375
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.20
    0.21
    288
    +0.13
    0.20
    241
    +0.12
    0.09
    Negative Logits
    slow
    -0.84
    nee
    -0.74
    SPA
    -0.71
     constitu
    -0.69
     Amateur
    -0.68
     Bern
    -0.68
     ATP
    -0.68
     antigen
    -0.66
    BRE
    -0.65
    adal
    -0.64
    POSITIVE LOGITS
     crates
    1.11
     Crate
    1.01
     loot
    1.01
     looted
    1.01
     trove
    1.00
     containers
    0.99
     hoard
    0.98
     stash
    0.91
     haul
    0.87
    iture
    0.87
    Activations Density 7.685%

    No Known Activations