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. 44877
    Prev
    Next
    INDEX
    Explanations

    words related to screens or displays

    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
    +0.21
    0.9%
    99
    +0.13
    0.5%
    578
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.21
    0.10
    532
    +0.13
    0.07
    486
    +0.12
    0.03
    Negative Logits
    doms
    -0.80
    ghan
    -0.80
     Carnegie
    -0.71
    ortium
    -0.71
    icably
    -0.70
     plur
    -0.69
    aternal
    -0.69
    istan
    -0.67
     caution
    -0.66
    ongo
    -0.66
    POSITIVE LOGITS
    plays
    1.44
    printed
    1.10
    tops
    1.07
    caps
    1.04
    writers
    1.03
     screens
    0.99
    writer
    0.95
     TVs
    0.94
    grab
    0.94
    writing
    0.93
    Activations Density 10.060%

    No Known Activations