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. 13197
    Prev
    Next
    INDEX
    Explanations

    people's names containing a specific pattern, specifically names ending in 'yn'

    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
    356
    +0.12
    0.5%
    99
    +0.11
    0.5%
    223
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.12
    0.08
    291
    +0.11
    0.09
    29
    +0.11
    0.10
    Negative Logits
     bearer
    -0.69
     ARTICLE
    -0.66
    ãĥ¼ãĥ³
    -0.66
     Archangel
    -0.64
    HAEL
    -0.64
    ALLY
    -0.63
     Shinra
    -0.63
     LIFE
    -0.62
     ACTION
    -0.62
    lessly
    -0.62
    POSITIVE LOGITS
    osure
    0.88
    nen
    0.87
    emy
    0.86
    ucle
    0.85
    swer
    0.83
    ergic
    0.83
    anny
    0.81
    thia
    0.81
    pher
    0.80
    emies
    0.80
    Activations Density 8.398%

    No Known Activations