Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 34060
    Prev
    Next
    INDEX
    Explanations

    phrases related to wearing physical objects or accessories on the body

    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
    0.8%
    420
    +0.13
    0.5%
    554
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.34
    640
    +0.13
    0.29
    397
    +0.13
    0.08
    Negative Logits
    llor
    -0.91
    ancock
    -0.91
    terness
    -0.89
    iets
    -0.85
    emetery
    -0.85
    eport
    -0.81
    ezvous
    -0.81
    enario
    -0.78
     Dhabi
    -0.78
    agonist
    -0.77
    POSITIVE LOGITS
     sleeves
    1.17
     clothes
    1.13
     shirt
    1.08
     jacket
    1.06
     socks
    1.05
     pants
    1.04
     robes
    1.03
     camouflage
    1.03
     underwear
    1.02
     gloves
    1.01
    Activations Density 18.873%

    No Known Activations