© 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. 4858
    Prev
    Next
    INDEX
    Explanations

    information related to marijuana, cannabis strains, cannabis appreciation, and medical conditions like burns and injuries

    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
    +0.16
    0.7%
    387
    +0.11
    0.5%
    750
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.16
    0.12
    191
    +0.11
    0.07
    351
    +0.10
    0.05
    Negative Logits
    ku
    -0.95
    kt
    -0.81
    liam
    -0.79
    ãĤ©
    -0.76
    kus
    -0.74
    utm
    -0.71
    kh
    -0.71
    bal
    -0.69
    atl
    -0.68
    last
    -0.68
    POSITIVE LOGITS
     nor
    1.10
     whatsoever
    1.04
     anymore
    1.02
    erno
    0.76
     anywhere
    0.71
     slightest
    0.69
     detectable
    0.65
    ;}
    0.65
    omatic
    0.65
     Spray
    0.64
    Activations Density 21.315%

    No Known Activations