© 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. 33124
    Prev
    Next
    INDEX
    Explanations

    technical terms related to convenience and efficiency

    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
    +0.17
    0.9%
    642
    +0.13
    0.7%
    288
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.17
    0.15
    36
    +0.13
    0.16
    159
    +0.11
    0.10
    Negative Logits
    raid
    -0.65
    authorized
    -0.65
    song
    -0.65
    ynt
    -0.64
    WAR
    -0.61
    orn
    -0.61
    cham
    -0.60
    otiation
    -0.60
    ethical
    -0.59
    antam
    -0.58
    POSITIVE LOGITS
     convenient
    0.91
    ãĥ¼ãĥĨ
    0.80
    venient
    0.76
     convenience
    0.76
     conven
    0.75
     conveniently
    0.74
     excuse
    0.67
     inconven
    0.67
    oire
    0.65
     shortcuts
    0.64
    Activations Density 10.170%

    No Known Activations