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. 4407
    Prev
    Next
    INDEX
    Explanations

    references to writing instruments, specifically pencils

    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
    289
    +0.14
    0.6%
    383
    +0.11
    0.5%
    754
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.22
    289
    +0.11
    0.03
    288
    +0.11
    0.21
    Negative Logits
    COMPLE
    -0.80
    ULTS
    -0.80
    REC
    -0.79
    EEE
    -0.77
    ELF
    -0.77
    STATE
    -0.72
    CBS
    -0.71
    ccoli
    -0.70
    κ
    -0.70
    ItemTracker
    -0.69
    POSITIVE LOGITS
    ibrary
    1.03
    ounge
    1.02
    ateral
    1.01
    opez
    1.00
    edo
    0.97
    ength
    0.97
    ocity
    0.94
    ues
    0.93
    ution
    0.92
    anguage
    0.91
    Activations Density 7.369%

    No Known Activations