© 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. 31672
    Prev
    Next
    INDEX
    Explanations

    phrases related to political biases or controversies

    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
    459
    +0.09
    0.5%
    477
    +0.08
    0.5%
    548
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.09
    0.14
    477
    +0.08
    0.09
    314
    +0.07
    -0.07
    Negative Logits
    azeera
    -0.62
    enhagen
    -0.55
     involuntary
    -0.51
    iard
    -0.47
     delegate
    -0.46
    Ô
    -0.45
     treadmill
    -0.45
     backfield
    -0.45
     escal
    -0.44
     jog
    -0.44
    POSITIVE LOGITS
    Ī
    0.58
    ï¸
    0.55
     Flask
    0.53
    Ü
    0.52
    axis
    0.52
    ciation
    0.51
    /
    0.51
    âĿ
    0.49
    ×Ļ
    0.49
    å§
    0.49
    Activations Density 14.687%

    No Known Activations