© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 386
    Prev
    Next
    INDEX
    Explanations

    phrases conveying lack of association or relevance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    446
    +0.14
    0.5%
    726
    +0.13
    0.4%
    554
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.14
    0.03
    455
    +0.13
    0.03
    119
    +0.12
    0.03
    Negative Logits
    atures
    -0.96
    shr
    -0.89
    §
    -0.87
    rique
    -0.86
    sbm
    -0.86
     halves
    -0.86
    Reviewer
    -0.86
    pa
    -0.85
    uru
    -0.84
    animous
    -0.83
    POSITIVE LOGITS
    ozy
    1.00
    xx
    0.95
    FTWARE
    0.92
    hing
    0.91
    OOL
    0.89
    agra
    0.88
    berman
    0.88
    uating
    0.87
     whatsoever
    0.87
     sit
    0.87
    Activations Density 0.213%

    No Known Activations