© 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. 39497
    Prev
    Next
    INDEX
    Explanations

    phrases related to veracity and accuracy in information

    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
    526
    +0.10
    0.5%
    35
    +0.09
    0.5%
    506
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.15
    326
    +0.09
    0.15
    345
    +0.09
    0.07
    Negative Logits
    NetMessage
    -0.58
    ENS
    -0.54
    ered
    -0.53
    oresc
    -0.53
    ENDED
    -0.51
    ennes
    -0.51
     Towns
    -0.50
     Rh
    -0.50
     Fever
    -0.49
     euth
    -0.49
    POSITIVE LOGITS
    itable
    0.84
    ulent
    0.81
    bat
    0.79
    ifiable
    0.79
    ulence
    0.74
    istically
    0.70
    itably
    0.69
    bly
    0.67
    theless
    0.66
    bling
    0.66
    Activations Density 3.807%

    No Known Activations