© 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 EvalsExportsinterp-engineNEWAPI 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 Local
    9. 6-RES_SCL-AJT
    11. 31711
    Prev
    Next
    INDEX
    Explanations

    the term "fact" in various contexts

    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
    +0.25
    1.0%
    213
    +0.13
    0.5%
    651
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.25
    0.06
    636
    +0.13
    0.05
    642
    +0.13
    0.02
    Negative Logits
    avorite
    -1.01
     livest
    -0.81
    ESE
    -0.76
    airs
    -0.75
    itsch
    -0.74
     awa
    -0.72
    asca
    -0.71
     lungs
    -0.70
    interstitial
    -0.69
    artney
    -0.69
    POSITIVE LOGITS
    ually
    1.27
    ional
    1.22
    uality
    1.18
    orial
    1.15
    itious
    1.03
    oids
    0.98
    uate
    0.95
    uation
    0.90
    finding
    0.88
    ual
    0.87
    Activations Density 5.900%

    No Known Activations