© 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. 13926
    Prev
    Next
    INDEX
    Explanations

    test related keywords and code snippets, particularly focused on testing software applications

    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
    +0.23
    1.0%
    288
    +0.11
    0.5%
    216
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    210
    +0.23
    0.05
    651
    +0.11
    0.08
    690
    +0.11
    0.05
    Negative Logits
    theless
    -1.00
    etheless
    -0.84
    ignt
    -0.82
    taboola
    -0.81
    leans
    -0.77
    VIDIA
    -0.77
    vernment
    -0.77
    ACP
    -0.76
     traged
    -0.75
    rontal
    -0.74
    POSITIVE LOGITS
    osterone
    1.56
    imony
    1.44
    imon
    1.19
    udo
    1.05
    icles
    0.99
    icle
    0.94
    ifies
    0.93
     suite
    0.92
    aments
    0.89
    icular
    0.89
    Activations Density 7.779%

    No Known Activations