© 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. 33310
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "James" in various contexts, especially related to individuals and their 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
    +0.24
    1.0%
    430
    +0.13
    0.5%
    504
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.24
    0.08
    435
    +0.13
    0.05
    430
    +0.13
    0.12
    Negative Logits
    ajo
    -0.82
    cert
    -0.79
    sites
    -0.78
    employment
    -0.77
    cision
    -0.77
    ĻĤ
    -0.74
    favorite
    -0.73
    ģ«
    -0.73
    security
    -0.73
     stricken
    -0.72
    POSITIVE LOGITS
     Harden
    1.09
     Madison
    1.07
     Webb
    1.03
     Potter
    1.02
     Roberts
    0.99
     Joyce
    0.98
     Franco
    0.98
    sburg
    0.98
     Beard
    0.97
     Holmes
    0.97
    Activations Density 5.342%

    No Known Activations