© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 252
    Prev
    Next
    INDEX
    Explanations

    phrases related to various topics such as community issues, health care reform, and economic policies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    393
    +0.16
    0.6%
    326
    +0.15
    0.5%
    431
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.16
    0.08
    431
    +0.15
    0.08
    661
    +0.12
    0.07
    Negative Logits
     Lauder
    -0.87
    Reviewer
    -0.77
    spin
    -0.70
     smear
    -0.69
    fman
    -0.67
     resorts
    -0.66
     Britons
    -0.65
     shifts
    -0.65
     Authorities
    -0.65
     Numbers
    -0.65
    POSITIVE LOGITS
    atisf
    1.06
    selves
    1.02
     happening
    1.00
    uddenly
    1.00
    ought
    0.99
    ̶
    0.99
    kaya
    0.98
    omething
    0.97
    lightly
    0.97
     happened
    0.94
    Activations Density 0.577%

    No Known Activations