© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 34026
    Prev
    Next
    INDEX
    Explanations

    references to medical contracts and negotiations

    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
    +0.22
    1.3%
    679
    +0.08
    0.5%
    208
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    209
    +0.22
    0.10
    575
    +0.08
    0.17
    330
    +0.08
    0.10
    Negative Logits
     Tropical
    -0.62
     Territories
    -0.58
     Worm
    -0.56
     Virus
    -0.55
    osure
    -0.54
    atever
    -0.52
    Poké
    -0.52
    Shock
    -0.50
    izoph
    -0.48
    lished
    -0.47
    POSITIVE LOGITS
    hip
    0.91
    paces
    0.84
     unions
    0.76
    mith
    0.76
     union
    0.75
    hips
    0.72
    afety
    0.70
    '
    0.69
    pace
    0.61
    ervatives
    0.61
    Activations Density 13.145%

    No Known Activations