© 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. 46060
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software design and development

    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
    481
    +0.18
    0.8%
    495
    +0.11
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.18
    0.05
    570
    +0.11
    0.01
    756
    +0.10
    -0.16
    Negative Logits
    staking
    -0.62
    laughs
    -0.62
    annabin
    -0.62
     Colomb
    -0.60
    isSpecialOrderable
    -0.57
     âĢİ
    -0.57
    acly
    -0.56
     Gerr
    -0.56
    mittedly
    -0.56
     juven
    -0.56
    POSITIVE LOGITS
    ';
    0.68
    )?
    0.66
     Allows
    0.63
    adobe
    0.63
     (+
    0.62
     avg
    0.61
     Applicant
    0.60
     /
    0.60
     MFT
    0.60
    «ĺ
    0.60
    Activations Density 11.886%

    No Known Activations