© 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 Local
    9. 6-RES_SCL-AJT
    11. 35603
    Prev
    Next
    INDEX
    Explanations

    phrases related to Planned Parenthood and its 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
    +0.19
    1.0%
    343
    +0.10
    0.5%
    292
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.19
    0.06
    57
    +0.10
    0.04
    285
    +0.10
    0.03
    Negative Logits
    lass
    -0.67
     Logged
    -0.65
    obin
    -0.65
    eme
    -0.63
    emate
    -0.61
    emo
    -0.61
    wcsstore
    -0.60
    alys
    -0.59
    lasses
    -0.59
    Hug
    -0.59
    POSITIVE LOGITS
     Parenthood
    1.14
     Federation
    0.85
    arenthood
    0.76
     clinics
    0.73
     affiliates
    0.72
     Industries
    0.63
     Simulator
    0.61
     abortion
    0.60
     Clinic
    0.60
     lobb
    0.58
    Activations Density 6.319%

    No Known Activations