© 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. 39706
    Prev
    Next
    INDEX
    Explanations

    technical terms related to gravitational waves and physics concepts

    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
    199
    +0.13
    0.6%
    288
    +0.12
    0.6%
    565
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.13
    0.11
    253
    +0.12
    0.12
    633
    +0.11
    0.10
    Negative Logits
    ħĭ
    -0.78
    âķIJâķIJ
    -0.69
    eer
    -0.66
    @#&
    -0.61
     FSA
    -0.59
    OOL
    -0.59
    ĪĴ
    -0.58
    aneous
    -0.58
    HOME
    -0.57
    VIDEO
    -0.57
    POSITIVE LOGITS
    itas
    1.23
    itating
    1.23
    estones
    1.12
    ities
    1.10
    itates
    1.05
    itate
    1.04
    estone
    1.03
    itated
    1.03
    itation
    1.02
    itations
    0.93
    Activations Density 5.788%

    No Known Activations