© 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 3447
    Prev
    Next
    INDEX
    Explanations

    phrases related to large amounts of money or financial figures

    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
    288
    +0.18
    0.6%
    1
    +0.13
    0.4%
    471
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.18
    0.05
    542
    +0.13
    0.05
    432
    +0.13
    0.04
    Negative Logits
    pring
    -0.98
    yrinth
    -0.96
     Anarchy
    -0.96
    drawn
    -0.95
    odox
    -0.93
    DER
    -0.92
    fan
    -0.90
    der
    -0.90
    imen
    -0.90
    ebin
    -0.89
    POSITIVE LOGITS
     dollars
    1.54
    dollar
    1.39
     pounds
    1.25
     dollar
    1.24
    naire
    1.17
    atform
    1.17
     gallons
    1.17
    undo
    1.16
     annually
    1.14
    thal
    1.13
    Activations Density 0.356%

    No Known Activations