© 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
    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. 13918
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "make good" indicating the fulfillment of promises or commitments

    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
    71
    +0.16
    0.6%
    699
    +0.12
    0.5%
    570
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.16
    0.12
    408
    +0.12
    0.18
    344
    +0.12
    0.14
    Negative Logits
    anwhile
    -0.84
     Creator
    -0.75
    enne
    -0.73
    IDS
    -0.72
    ioxide
    -0.72
     horizont
    -0.71
     Signed
    -0.70
     Niet
    -0.70
    wx
    -0.70
    ħĭ
    -0.69
    POSITIVE LOGITS
     impression
    1.10
    sense
    1.08
     dent
    0.91
     contribution
    0.87
     landfall
    0.85
     noises
    0.84
     allowance
    0.82
     sense
    0.82
     strides
    0.81
     fuss
    0.78
    Activations Density 11.410%

    No Known Activations