© 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 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. 33321
    Prev
    Next
    INDEX
    Explanations

    positions of authority or leadership

    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
    35
    +0.12
    0.5%
    685
    +0.11
    0.4%
    319
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    681
    +0.12
    0.06
    319
    +0.11
    0.05
    401
    +0.11
    0.07
    Negative Logits
    anwhile
    -0.98
    itsch
    -0.86
    alon
    -0.84
    tics
    -0.82
     Brist
    -0.82
    affles
    -0.80
    wana
    -0.80
     Carnegie
    -0.79
    ONES
    -0.78
    ulu
    -0.78
    POSITIVE LOGITS
     versa
    1.74
    hum
    1.00
     mate
    0.88
    ners
    0.87
    quel
    0.84
    ned
    0.83
    hal
    0.82
     vice
    0.81
    reg
    0.81
    iously
    0.80
    Activations Density 4.382%

    No Known Activations