© 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. 11470
    Prev
    Next
    INDEX
    Explanations

    words related to German language and politics

    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
    560
    +0.14
    0.7%
    458
    +0.14
    0.6%
    385
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.03
    232
    +0.14
    0.03
    560
    +0.12
    0.03
    Negative Logits
    adra
    -0.83
    thens
    -0.82
    eteenth
    -0.78
    hered
    -0.77
    atron
    -0.77
    ramid
    -0.77
    dullah
    -0.76
    6666
    -0.76
    LER
    -0.75
    ISIS
    -0.75
    POSITIVE LOGITS
     Univers
    0.91
     Antiqu
    0.84
     Volks
    0.82
     Identity
    0.82
     Instit
    0.78
     Mn
    0.76
     Defenders
    0.76
     Ide
    0.76
     Polic
    0.74
     Spy
    0.74
    Activations Density 0.163%

    No Known Activations