© 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. 13121
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to different projects and initiatives

    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
    218
    +0.17
    0.7%
    447
    +0.17
    0.7%
    651
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.17
    0.08
    659
    +0.17
    0.08
    117
    +0.15
    0.09
    Negative Logits
    taboola
    -0.91
    aws
    -0.81
    ously
    -0.78
    combe
    -0.78
    ^^^^
    -0.77
    acies
    -0.76
    ãģĦ
    -0.75
    anguage
    -0.74
    inders
    -0.73
    bane
    -0.72
    POSITIVE LOGITS
     Gutenberg
    1.55
    ion
    1.17
    ions
    1.15
    ioned
    1.02
     Ara
    0.89
    ional
    0.88
    eur
    0.88
    ually
    0.86
    ION
    0.83
    ors
    0.82
    Activations Density 3.171%

    No Known Activations