© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 32543
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and economic discussions, particularly focused on implications of government decisions and legislative actions

    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
    +0.16
    1.1%
    385
    +0.10
    0.7%
    150
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.17
    116
    +0.10
    0.06
    77
    +0.09
    0.05
    Negative Logits
    actor
    -0.55
    ographs
    -0.53
    oeuv
    -0.50
    aum
    -0.50
    itia
    -0.48
    OGR
    -0.48
    enough
    -0.48
    ographies
    -0.48
    uana
    -0.47
    cester
    -0.47
    POSITIVE LOGITS
     shutdown
    0.65
     aver
    0.56
     standoff
    0.55
     prevention
    0.52
     Shutdown
    0.51
     plag
    0.50
    ascus
    0.50
     showdown
    0.47
     shortened
    0.47
    ukong
    0.47
    Activations Density 5.871%

    No Known Activations