© 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. 36302
    Prev
    Next
    INDEX
    Explanations

    card names and attributes in the context of a specific card game

    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
    28
    +0.11
    0.6%
    414
    +0.11
    0.6%
    245
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.11
    0.02
    24
    +0.11
    0.05
    28
    +0.10
    0.06
    Negative Logits
     HIP
    -0.84
     Rodrig
    -0.63
     Philips
    -0.62
     HIT
    -0.61
     Volunte
    -0.60
     Hue
    -0.60
     ESA
    -0.59
     Fit
    -0.59
     Sirius
    -0.59
     Engels
    -0.58
    POSITIVE LOGITS
     mana
    0.91
     cards
    0.89
     decks
    0.84
    magic
    0.78
     orcs
    0.77
     Cards
    0.75
    Spell
    0.74
     enchantment
    0.74
     spell
    0.74
     spells
    0.73
    Activations Density 12.897%

    No Known Activations