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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 34079
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms and concepts

    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
    +0.25
    1.3%
    521
    +0.10
    0.5%
    260
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.25
    0.34
    14
    +0.10
    0.08
    255
    +0.09
    0.14
    Negative Logits
    inventoryQuantity
    -0.72
    igraph
    -0.69
     Offense
    -0.58
     Topic
    -0.56
     Antiqu
    -0.56
     Neighbor
    -0.55
    yi
    -0.55
     ancestor
    -0.55
    addons
    -0.55
    osponsors
    -0.55
    POSITIVE LOGITS
     disastrous
    0.64
     abundantly
    0.60
     astounding
    0.59
     predictably
    0.58
     devastating
    0.57
     priceless
    0.56
     undeniable
    0.56
    ãĤª
    0.54
     spectacular
    0.53
     inex
    0.53
    Activations Density 16.921%

    No Known Activations