© 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. 14186
    Prev
    Next
    INDEX
    Explanations

    adjectives related to comparative value or degree, such as "lesser" and "greater."

    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
    497
    +0.11
    0.5%
    569
    +0.11
    0.5%
    674
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.11
    0.15
    99
    +0.11
    0.10
    61
    +0.10
    0.09
    Negative Logits
     Pinball
    -0.76
    alys
    -0.74
    lon
    -0.66
    Cola
    -0.63
    retty
    -0.63
    Keys
    -0.63
    raltar
    -0.63
    La
    -0.61
    aly
    -0.61
    ushima
    -0.61
    POSITIVE LOGITS
     sized
    0.99
     lesser
    0.89
     minded
    0.87
     than
    0.87
    etheless
    0.82
     halves
    0.81
    parts
    0.78
     fractions
    0.77
    asar
    0.73
    iating
    0.72
    Activations Density 6.850%

    No Known Activations