© 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. 35655
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and issues

    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
    +0.21
    0.8%
    174
    +0.16
    0.7%
    16
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.21
    0.25
    213
    +0.16
    0.09
    14
    +0.15
    0.06
    Negative Logits
    WARD
    -0.97
     lockout
    -0.88
    ITED
    -0.82
     visitation
    -0.81
    ãĤĬ
    -0.79
    è»
    -0.79
     Reloaded
    -0.79
    PORT
    -0.78
    ãĥ¼ãĥĨãĤ£
    -0.77
     "$:/
    -0.77
    POSITIVE LOGITS
    amps
    1.35
    aos
    1.31
    unks
    1.28
    isel
    1.25
    annels
    1.24
    orus
    1.21
    ivas
    1.21
    illing
    1.20
    ieft
    1.19
    ubby
    1.17
    Activations Density 13.584%

    No Known Activations