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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 716
    Prev
    Next
    INDEX
    Explanations

    phrases related to numerical quantities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    647
    +0.14
    0.5%
    742
    +0.14
    0.5%
    392
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.14
    0.09
    625
    +0.14
    0.07
    225
    +0.13
    0.08
    Negative Logits
     Brief
    -0.95
    ataka
    -0.92
    ħĭ
    -0.86
     Commissioner
    -0.84
    imir
    -0.81
    rones
    -0.81
    ļéĨĴ
    -0.80
    imer
    -0.79
     Dull
    -0.78
    inis
    -0.77
    POSITIVE LOGITS
     (>
    1.44
     (~
    1.15
     (<
    1.05
     of
    1.05
    bang
    1.01
    UID
    0.95
    ÙĪ
    0.87
    Downloadha
    0.85
     thereof
    0.84
     imaginable
    0.82
    Activations Density 1.651%

    No Known Activations