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. 34101
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical processing or queuing of tasks

    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
    515
    +0.15
    0.7%
    749
    +0.13
    0.6%
    447
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.21
    326
    +0.13
    0.18
    575
    +0.13
    0.14
    Negative Logits
    sburg
    -0.69
     Eagles
    -0.69
    sonian
    -0.67
    ãĥŁ
    -0.67
     Hers
    -0.66
    BALL
    -0.65
     bats
    -0.65
    ographic
    -0.65
     Dortmund
    -0.65
    aryl
    -0.65
    POSITIVE LOGITS
    erness
    1.21
    ues
    1.04
     Que
    1.02
    zon
    1.01
    queue
    1.00
    uing
    0.98
    ue
    0.93
    ued
    0.92
    iu
    0.88
    ette
    0.88
    Activations Density 5.071%

    No Known Activations