© 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. 32757
    Prev
    Next
    INDEX
    Explanations

    information related to character abilities and traits, including powers, resistances, and effects

    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
    326
    +0.14
    0.5%
    160
    +0.13
    0.5%
    687
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.07
    597
    +0.13
    0.05
    570
    +0.12
    -0.01
    Negative Logits
    76561
    -1.01
     è£ıè
    -0.99
    à¼
    -0.98
    çĶ°
    -0.95
    acion
    -0.95
    Ò
    -0.93
    tein
    -0.92
    ãĥ¼ãĥĨãĤ£
    -0.90
     LH
    -0.90
    ZA
    -0.89
    POSITIVE LOGITS
     Arcane
    1.28
     Dexterity
    1.28
     sorcerer
    1.22
     nec
    1.21
    spell
    1.19
     Spell
    1.18
     arcane
    1.17
     mage
    1.15
     Charisma
    1.15
     cleric
    1.14
    Activations Density 11.578%

    No Known Activations