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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 34319
    Prev
    Next
    INDEX
    Explanations

    medical terms and information

    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
    +0.15
    0.6%
    122
    +0.14
    0.5%
    510
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.27
    146
    +0.14
    0.10
    288
    +0.12
    0.24
    Negative Logits
     comprom
    -0.74
     Quan
    -0.72
    isations
    -0.70
    izations
    -0.67
     almonds
    -0.66
     Oaks
    -0.65
     Rapp
    -0.64
     rall
    -0.63
    KING
    -0.63
    oyd
    -0.62
    POSITIVE LOGITS
    EStream
    1.00
     âĨ
    0.96
     âĨij
    0.95
    idepress
    0.85
     <+
    0.82
     CrossRef
    0.82
     Âł Âł
    0.81
     Âł Âł Âł Âł
    0.78
     âĨĴ
    0.77
     +++
    0.76
    Activations Density 13.105%

    No Known Activations