© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 34701
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engine performance and control mechanisms

    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
    496
    +0.04
    0.5%
    213
    +0.03
    0.5%
    609
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.04
    0.24
    408
    +0.03
    0.14
    540
    +0.03
    0.14
    Negative Logits
    arium
    -0.27
    ologies
    -0.26
    ites
    -0.26
    ****
    -0.25
    print
    -0.25
    acio
    -0.25
    ********
    -0.25
    eries
    -0.25
    *****
    -0.25
    aurus
    -0.24
    POSITIVE LOGITS
     punishment
    0.24
    rontal
    0.24
     msec
    0.23
     rainfall
    0.23
    etheless
    0.23
     emission
    0.22
    intensity
    0.22
     amount
    0.22
     saline
    0.22
     stun
    0.22
    Activations Density 5.898%

    No Known Activations