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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 45590
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial news articles

    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
    447
    +0.32
    1.6%
    481
    +0.10
    0.5%
    529
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.32
    0.22
    67
    +0.10
    0.25
    232
    +0.10
    0.19
    Negative Logits
     recess
    -0.86
     poem
    -0.75
     extraord
    -0.73
    ĸļ
    -0.72
     vag
    -0.70
     quo
    -0.70
     narration
    -0.68
     righteousness
    -0.67
     trope
    -0.67
     impe
    -0.65
    POSITIVE LOGITS
    Shares
    1.15
    Company
    1.04
     Holdings
    1.02
     subsidiaries
    0.93
    Companies
    0.92
     Employees
    0.89
     Labs
    0.89
     Telecom
    0.88
     Corp
    0.86
    Sales
    0.86
    Activations Density 16.480%

    No Known Activations