© 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. 1082
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and devices

    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
    640
    +0.20
    1.1%
    679
    +0.16
    0.9%
    745
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.20
    0.35
    640
    +0.16
    0.41
    679
    +0.09
    0.39
    Negative Logits
    icity
    -0.77
    usha
    -0.68
    ipel
    -0.67
    elle
    -0.65
     purse
    -0.64
    arily
    -0.62
     conservatism
    -0.62
     independ
    -0.61
     gobl
    -0.61
    iver
    -0.61
    POSITIVE LOGITS
     Thankfully
    0.81
     Granted
    0.80
     Unfortunately
    0.79
     However
    0.77
     Luckily
    0.75
     Compared
    0.74
     Fortunately
    0.74
     Needless
    0.73
     Canaver
    0.73
     Conversely
    0.73
    Activations Density 15.015%

    No Known Activations