© 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. 35298
    Prev
    Next
    INDEX
    Explanations

    words related to political figures and events

    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
    +0.14
    0.6%
    102
    +0.14
    0.6%
    326
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.14
    327
    +0.14
    0.08
    102
    +0.13
    0.10
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.87
    éĹĺ
    -0.84
    ioxide
    -0.79
     EntityItem
    -0.75
    ORTS
    -0.75
    IELD
    -0.75
     htt
    -0.74
    DragonMagazine
    -0.73
     Norn
    -0.70
     Sons
    -0.68
    POSITIVE LOGITS
    ving
    1.19
    aches
    1.10
    cks
    1.09
    crow
    1.08
    verbs
    1.04
    ger
    1.04
    dy
    1.04
    der
    1.03
    ve
    1.01
    aching
    1.00
    Activations Density 4.084%

    No Known Activations