© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 35292
    Prev
    Next
    INDEX
    Explanations

    phrases related to ethical values and moral dilemmas

    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
    +0.31
    1.3%
    99
    +0.13
    0.6%
    624
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.31
    0.30
    362
    +0.13
    0.17
    608
    +0.10
    0.21
    Negative Logits
    bol
    -0.71
    GE
    -0.71
    JV
    -0.70
    Reviewer
    -0.69
    potion
    -0.69
    oke
    -0.68
    elling
    -0.67
    INS
    -0.67
    LS
    -0.67
    GH
    -0.66
    POSITIVE LOGITS
    eatures
    0.84
     stages
    0.76
     disciplines
    0.76
     phases
    0.73
    ĸļ
    0.68
    ciating
    0.67
     intermedi
    0.66
    ModLoader
    0.65
     XD
    0.64
    oples
    0.64
    Activations Density 12.792%

    No Known Activations