© 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. 33324
    Prev
    Next
    INDEX
    Explanations

    words related to death and condolences

    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
    85
    +0.04
    0.5%
    218
    +0.03
    0.5%
    48
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    727
    +0.04
    0.05
    85
    +0.03
    0.06
    604
    +0.03
    0.04
    Negative Logits
    naires
    -0.23
    ieri
    -0.22
    endment
    -0.22
     park
    -0.21
     Collider
    -0.20
     lod
    -0.20
     Hunters
    -0.19
     Belle
    -0.19
    naire
    -0.19
    apolis
    -0.19
    POSITIVE LOGITS
    RIP
    0.36
     RIP
    0.27
    viation
    0.24
    istani
    0.24
    bons
    0.23
    cus
    0.23
    riots
    0.22
    LEY
    0.22
    face
    0.21
    faces
    0.21
    Activations Density 3.574%

    No Known Activations