© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2571
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and civil liberties, particularly emphasizing the concept of freedom

    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
    288
    +0.32
    1.0%
    311
    +0.18
    0.6%
    376
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.32
    0.09
    224
    +0.18
    0.07
    724
    +0.17
    0.07
    Negative Logits
    ergy
    -1.24
    liam
    -1.20
    ded
    -1.09
    eor
    -1.06
    assium
    -1.04
    enegger
    -1.04
    mers
    -1.03
    olf
    -1.00
    enna
    -1.00
    nos
    -0.99
    POSITIVE LOGITS
    bies
    1.19
    fulness
    1.18
     roam
    1.17
    urities
    1.07
    veland
    1.07
    yip
    1.07
    bringer
    1.03
     Fighters
    1.02
     guaranteed
    1.02
    lessness
    1.00
    Activations Density 1.056%

    No Known Activations