© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    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. 31833
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings or court-related activities

    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
    1.0%
    657
    +0.15
    0.6%
    178
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    657
    +0.25
    0.13
    746
    +0.15
    0.04
    166
    +0.13
    0.09
    Negative Logits
    ï¸ı
    -0.88
    jiang
    -0.85
    mson
    -0.79
     Saban
    -0.77
     Pyro
    -0.75
    ku
    -0.74
     Motorsport
    -0.71
     livest
    -0.71
    resso
    -0.70
     plent
    -0.69
    POSITIVE LOGITS
    rooms
    1.32
    esan
    1.18
    room
    1.14
    auld
    1.03
     proceedings
    0.96
    breakers
    0.95
     hearings
    0.94
    wright
    0.90
    breaker
    0.90
    frames
    0.90
    Activations Density 10.147%

    No Known Activations