© 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. 4628
    Prev
    Next
    INDEX
    Explanations

    pieces of text mentioning the word "Breitbart"

    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
    137
    +0.11
    0.7%
    220
    +0.09
    0.6%
    343
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.23
    220
    +0.09
    0.08
    302
    +0.09
    0.12
    Negative Logits
    ãħĭ
    -0.60
    å°Ĩ
    -0.55
     hemor
    -0.54
     Palestin
    -0.54
    ournal
    -0.53
    iating
    -0.50
    iates
    -0.49
    iate
    -0.49
    ives
    -0.47
     crumbling
    -0.46
    POSITIVE LOGITS
    itbart
    0.85
    tto
    0.66
    zos
    0.65
    xit
    0.63
    vity
    0.63
    bre
    0.63
    tt
    0.60
    cht
    0.60
    viation
    0.59
    vi
    0.56
    Activations Density 9.102%

    No Known Activations