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. 34447
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various individuals in different contexts

    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
    373
    +0.13
    1.0%
    218
    +0.08
    0.6%
    497
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.17
    373
    +0.08
    -0.08
    659
    +0.07
    0.16
    Negative Logits
    tumblr
    -0.48
    elsius
    -0.44
     Generations
    -0.41
     torch
    -0.40
     rupture
    -0.39
    caps
    -0.38
    ilogy
    -0.38
    FORMATION
    -0.38
    ategory
    -0.38
    ATURE
    -0.38
    POSITIVE LOGITS
    berto
    0.54
     Olivier
    0.51
    jen
    0.51
    ko
    0.50
    ijn
    0.49
     Hend
    0.46
     Koen
    0.46
    Andre
    0.46
    jan
    0.46
     Stephan
    0.45
    Activations Density 3.156%

    No Known Activations