© 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. 14633
    Prev
    Next
    INDEX
    Explanations

    stock market-related information, including company names and stock symbols

    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
    364
    +0.11
    0.4%
    129
    +0.11
    0.4%
    6
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    627
    +0.11
    0.03
    333
    +0.11
    0.03
    767
    +0.11
    0.03
    Negative Logits
     interpol
    -0.91
     squats
    -0.84
    ests
    -0.81
     disse
    -0.80
     tracts
    -0.78
     boun
    -0.76
     decomp
    -0.76
     tyr
    -0.75
    ilege
    -0.75
     inval
    -0.75
    POSITIVE LOGITS
    DAQ
    1.38
    NYSE
    1.33
    +)
    1.26
    )'
    1.17
    )-
    1.15
    )+
    1.12
    )[
    1.12
    )=
    1.11
    )]
    1.10
    ))
    1.10
    Activations Density 0.227%

    No Known Activations