© 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. 34861
    Prev
    Next
    INDEX
    Explanations

    mentions of financial and investment terms, possibly related to cryptocurrency or blockchain technology

    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
    +0.38
    1.7%
    314
    +0.15
    0.7%
    481
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.38
    -0.04
    167
    +0.15
    -0.00
    659
    +0.12
    0.19
    Negative Logits
    enegger
    -0.86
     semblance
    -0.72
     throne
    -0.71
     vanished
    -0.70
    Äĩ
    -0.69
     offence
    -0.69
     foreground
    -0.69
     uncont
    -0.68
     routine
    -0.68
     wagon
    -0.67
    POSITIVE LOGITS
     Magazine
    1.12
    Week
    1.06
    Street
    1.02
    News
    1.01
    Politics
    0.96
    Blog
    0.96
    Media
    0.95
    Web
    0.95
    Wire
    0.95
    Nation
    0.93
    Activations Density 19.378%

    No Known Activations