© 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
    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. 32158
    Prev
    Next
    INDEX
    Explanations

    terms related to political debates and compromises

    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
    739
    +0.11
    0.5%
    292
    +0.10
    0.5%
    178
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.11
    0.08
    659
    +0.10
    0.08
    23
    +0.10
    0.08
    Negative Logits
    Bug
    -0.88
    Adds
    -0.79
    Poor
    -0.78
    Aren
    -0.78
    Pac
    -0.77
    Circ
    -0.77
    Chart
    -0.75
    Pin
    -0.74
    Manufact
    -0.74
    Card
    -0.73
    POSITIVE LOGITS
    Ħ¢
    0.74
     tease
    0.64
     ni
    0.64
     Misty
    0.63
     sher
    0.63
     JUSTICE
    0.62
     i
    0.61
     li
    0.60
     e
    0.60
     ]
    0.60
    Activations Density 7.063%

    No Known Activations