© 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. 1521
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    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
    115
    +0.16
    0.5%
    130
    +0.14
    0.4%
    592
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.16
    0.07
    232
    +0.14
    0.06
    639
    +0.13
    0.07
    Negative Logits
    çīĪ
    -1.35
    atform
    -1.01
     Kinnikuman
    -0.96
     Skydragon
    -0.92
     AX
    -0.90
     Eternity
    -0.90
    å°Ĩ
    -0.85
     è£ıè
    -0.84
    )=(
    -0.83
     HDL
    -0.82
    POSITIVE LOGITS
    iman
    1.18
    cheat
    1.07
    icient
    1.07
    chal
    1.07
    jin
    1.05
    agin
    1.05
    uddin
    1.03
    alla
    0.98
    esi
    0.98
    idi
    0.98
    Activations Density 1.617%

    No Known Activations