© 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. 3749
    Prev
    Next
    INDEX
    Explanations

    references to political and social issues

    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
    459
    +0.09
    0.5%
    565
    +0.09
    0.5%
    551
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.09
    0.12
    570
    +0.09
    -0.02
    587
    +0.09
    0.13
    Negative Logits
    eez
    -0.52
    cheat
    -0.51
    ahs
    -0.49
    owler
    -0.49
    VERTIS
    -0.48
    ufact
    -0.47
    wagen
    -0.47
    earch
    -0.47
     slideshow
    -0.47
     professionals
    -0.46
    POSITIVE LOGITS
     thereto
    0.68
     linking
    0.63
     intertwined
    0.61
     link
    0.59
    ships
    0.58
    coe
    0.58
     slices
    0.56
    lined
    0.56
    tar
    0.56
    sided
    0.55
    Activations Density 15.239%

    No Known Activations