© 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. 34039
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to future events or actions

    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
    447
    +0.10
    1.1%
    468
    +0.06
    0.6%
    16
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    542
    +0.10
    0.09
    255
    +0.06
    0.11
    132
    +0.04
    0.09
    Negative Logits
     Vive
    -0.32
     Balanced
    -0.30
    mates
    -0.30
     Tib
    -0.28
     Gob
    -0.28
    azar
    -0.28
     Pug
    -0.28
    shared
    -0.28
     Pend
    -0.28
    unts
    -0.28
    POSITIVE LOGITS
    ?:
    0.40
     step
    0.36
    !?
    0.35
    ?,
    0.34
     unfold
    0.34
     emerge
    0.33
     steps
    0.33
    ?
    0.33
    ?!
    0.33
    .<
    0.32
    Activations Density 11.515%

    No Known Activations