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. 4506
    Prev
    Next
    INDEX
    Explanations

    phrases related to business and corporate matters

    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
    288
    +0.10
    0.7%
    447
    +0.10
    0.7%
    679
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.10
    0.10
    301
    +0.10
    0.08
    288
    +0.09
    0.19
    Negative Logits
    maxwell
    -0.51
    bra
    -0.50
    bat
    -0.49
    athon
    -0.47
    ttp
    -0.46
     Cage
    -0.45
    lite
    -0.44
    spir
    -0.43
    imar
    -0.43
    hus
    -0.43
    POSITIVE LOGITS
     subsidiary
    0.69
     subsidiaries
    0.65
    rador
    0.65
    itute
    0.58
    lisher
    0.57
    iaries
    0.49
    raint
    0.49
    onial
    0.48
    enture
    0.47
     detach
    0.47
    Activations Density 7.889%

    No Known Activations