© 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. 12483
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to deception or fake situations

    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
    357
    +0.03
    0.5%
    579
    +0.03
    0.4%
    460
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.03
    0.05
    444
    +0.03
    0.03
    326
    +0.03
    0.04
    Negative Logits
     Extrem
    -0.26
     Dynamics
    -0.21
     ostr
    -0.21
     aggrav
    -0.21
     pige
    -0.20
     Borough
    -0.20
     intercepted
    -0.20
    hower
    -0.20
     eggs
    -0.20
     apprehension
    -0.19
    POSITIVE LOGITS
    rooms
    0.28
    blers
    0.28
    arie
    0.25
    eless
    0.25
    arro
    0.25
    rock
    0.24
    pathic
    0.24
    itsu
    0.23
    ble
    0.23
     sham
    0.23
    Activations Density 0.393%

    No Known Activations