© 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
    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. 13847
    Prev
    Next
    INDEX
    Explanations

    names and terms relating to personal trainers and instructor training

    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
    +0.12
    0.7%
    575
    +0.12
    0.7%
    224
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.12
    0.11
    575
    +0.12
    0.14
    549
    +0.11
    0.08
    Negative Logits
     Pradesh
    -0.59
    peat
    -0.55
     Territories
    -0.53
    izons
    -0.50
    yss
    -0.50
    itious
    -0.48
     Transit
    -0.47
    itals
    -0.46
    ween
    -0.46
    itions
    -0.46
    POSITIVE LOGITS
     specializing
    0.71
     Valerie
    0.59
     extraord
    0.58
     trainer
    0.58
     Mehran
    0.57
    claimer
    0.56
     Erica
    0.53
     Vanessa
    0.52
    recomm
    0.52
     assistants
    0.51
    Activations Density 6.287%

    No Known Activations