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. 4138
    Prev
    Next
    INDEX
    Explanations

    references to personal computing, technology advancements, and innovative companies working on augmented reality devices

    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
    501
    +0.10
    0.6%
    578
    +0.08
    0.4%
    600
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.10
    -0.02
    362
    +0.08
    0.07
    28
    +0.08
    0.06
    Negative Logits
    wagen
    -0.73
    paio
    -0.70
    teness
    -0.69
    cular
    -0.63
    blem
    -0.63
    anthrop
    -0.63
    ibaba
    -0.62
    pora
    -0.61
    ļé
    -0.60
    asus
    -0.58
    POSITIVE LOGITS
     Email
    0.63
     Share
    0.62
     PsyNet
    0.62
     Featured
    0.61
     embed
    0.61
     Tickets
    0.61
     Quote
    0.60
     Events
    0.59
     Print
    0.59
     Comments
    0.57
    Activations Density 4.239%

    No Known Activations