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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 45249
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to mechanical gear components

    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
    1.2%
    326
    +0.15
    0.7%
    168
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.25
    0.05
    63
    +0.15
    0.08
    326
    +0.10
    0.18
    Negative Logits
     CTR
    -0.90
     Mub
    -0.76
    PsyNetMessage
    -0.69
     Sheen
    -0.65
    aukee
    -0.65
    CHAT
    -0.64
    enance
    -0.63
    iversal
    -0.63
     Mellon
    -0.62
     Quincy
    -0.61
    POSITIVE LOGITS
    box
    1.06
    boxes
    1.00
     gear
    0.93
    bag
    0.87
    bags
    0.79
    shift
    0.74
    gear
    0.70
     boxes
    0.69
    ifted
    0.68
     worn
    0.68
    Activations Density 7.099%

    No Known Activations