© 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5965
    Prev
    Next
    INDEX
    Explanations

    phrases related to the frequency of events, especially emphasizing rarity or infrequency

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    383
    +0.16
    0.6%
    195
    +0.14
    0.5%
    326
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.16
    0.08
    271
    +0.14
    0.06
    724
    +0.13
    0.09
    Negative Logits
    oÄŁ
    -1.01
    arching
    -1.01
    gur
    -0.99
    rongh
    -0.96
    tein
    -0.96
    agra
    -0.91
    odium
    -0.88
    afia
    -0.87
    mosp
    -0.86
    burgh
    -0.86
    POSITIVE LOGITS
    theless
    1.81
     occurrence
    1.32
     occurrences
    1.24
    uate
    1.19
    icably
    1.07
    soever
    1.03
     dime
    1.02
    entimes
    1.02
    tenance
    0.98
     charms
    0.98
    Activations Density 1.916%

    No Known Activations