© 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. 32861
    Prev
    Next
    INDEX
    Explanations

    proper titles or honorifics such as "Sir" or "Lady" before names

    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
    386
    +0.17
    0.6%
    447
    +0.16
    0.6%
    472
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.17
    0.09
    176
    +0.16
    0.05
    699
    +0.13
    0.02
    Negative Logits
     largeDownload
    -0.84
    EStream
    -0.79
     graft
    -0.79
     stabilization
    -0.78
    SHIP
    -0.76
    anwhile
    -0.76
     prelim
    -0.76
    ©¶æ
    -0.75
    ¥ŀ
    -0.74
    stocks
    -0.74
    POSITIVE LOGITS
    Sir
    1.00
    zech
    0.97
    leaf
    0.95
     Sir
    0.92
    ran
    0.90
    bridge
    0.89
     Laurent
    0.89
    acha
    0.89
    angelo
    0.88
    cliffe
    0.88
    Activations Density 6.202%

    No Known Activations