© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39529
    Prev
    Next
    INDEX
    Explanations

    dates and durations

    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
    +0.17
    0.7%
    761
    +0.12
    0.5%
    133
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.17
    0.16
    253
    +0.12
    0.17
    279
    +0.11
    0.14
    Negative Logits
    oria
    -0.65
    gments
    -0.63
    ees
    -0.62
    PAC
    -0.61
    lict
    -0.60
    ocalypse
    -0.60
     Divinity
    -0.58
    mia
    -0.58
    VK
    -0.57
     Defeat
    -0.57
    POSITIVE LOGITS
    ©¶æ
    1.02
     mornings
    0.99
    etheless
    0.94
    ilaterally
    0.94
    til
    0.91
    Lear
    0.91
     morning
    0.87
     evening
    0.84
     night
    0.84
     Noon
    0.84
    Activations Density 21.907%

    No Known Activations