© 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. 13018
    Prev
    Next
    INDEX
    Explanations

    verbs related to requesting, reporting, or demanding actions from others

    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
    745
    +0.08
    0.5%
    163
    +0.08
    0.5%
    148
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.08
    0.10
    745
    +0.08
    -0.13
    283
    +0.07
    0.01
    Negative Logits
     Stru
    -0.54
    stadt
    -0.52
    furt
    -0.51
     Tycoon
    -0.51
    ohyd
    -0.51
    stead
    -0.51
    Ĥ¬
    -0.51
     decad
    -0.48
     Sapp
    -0.48
    irtual
    -0.48
    POSITIVE LOGITS
     pardon
    0.67
     clarification
    0.64
     clarify
    0.61
     rhet
    0.58
     ransom
    0.58
     reconsider
    0.57
     postpone
    0.54
     renew
    0.54
     inquire
    0.53
     requ
    0.52
    Activations Density 8.993%

    No Known Activations