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

    Neuronpedia

    APICircuit 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. 45398
    Prev
    Next
    INDEX
    Explanations

    words related to eyewear production and tobacco manufacturing

    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
    481
    +0.14
    0.6%
    167
    +0.13
    0.5%
    591
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.34
    326
    +0.13
    0.33
    67
    +0.12
    0.22
    Negative Logits
    é¾įå¥ij士
    -1.00
    rawdownloadcloneembedreportprint
    -0.78
    DragonMagazine
    -0.77
     Akin
    -0.74
     Centauri
    -0.72
     soluble
    -0.72
    theless
    -0.72
     Dragonbound
    -0.71
     Bravo
    -0.70
     Preferred
    -0.69
    POSITIVE LOGITS
    Ģ
    1.21
    ª
    1.17
    ancies
    1.14
    ents
    1.13
    ĩ
    1.13
    ·
    1.09
    Ħ
    1.08
    ices
    1.08
    ants
    1.08
    itors
    1.08
    Activations Density 18.288%

    No Known Activations