© 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. 46068
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of "nothing" is emphasized or contrasted with something else

    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
    383
    +0.17
    0.7%
    447
    +0.15
    0.6%
    116
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.17
    0.11
    551
    +0.15
    0.08
    698
    +0.13
    0.07
    Negative Logits
    grad
    -0.79
    ocard
    -0.77
    asio
    -0.77
    ilt
    -0.76
    assis
    -0.74
     Appeal
    -0.72
    eg
    -0.70
     anonymity
    -0.70
    ushima
    -0.70
    idon
    -0.69
    POSITIVE LOGITS
     else
    1.53
    Else
    1.28
     whatsoever
    1.10
     Else
    0.98
     remotely
    0.98
     resembling
    0.90
     Flask
    0.89
     imaginable
    0.88
     bothering
    0.84
     worthwhile
    0.84
    Activations Density 6.329%

    No Known Activations