© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 12855
    Prev
    Next
    INDEX
    Explanations

    references to legal documents, permits, applications, and requests for various purposes

    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
    •Layer 6 UMAP region: Mixed in middle - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.16
    0.8%
    459
    +0.11
    0.6%
    253
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.16
    0.11
    253
    +0.11
    0.13
    383
    +0.10
    0.11
    Negative Logits
    feeding
    -0.66
    ottesville
    -0.60
    role
    -0.59
    ilight
    -0.59
    haul
    -0.58
    rodu
    -0.57
    pac
    -0.55
     Beef
    -0.55
    rench
    -0.55
    oxy
    -0.55
    POSITIVE LOGITS
     paperwork
    0.78
    URI
    0.76
     deadline
    0.74
     visas
    0.71
     submissions
    0.70
     filed
    0.69
     deadlines
    0.66
     Fee
    0.66
    Applic
    0.65
    ursed
    0.64
    Activations Density 8.899%

    No Known Activations