© 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. 40601
    Prev
    Next
    INDEX
    Explanations

    descriptions of various meetings

    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
    +0.28
    1.3%
    756
    +0.13
    0.6%
    68
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.28
    0.08
    283
    +0.13
    0.00
    640
    +0.10
    0.21
    Negative Logits
    cul
    -0.71
    duc
    -0.71
    oil
    -0.70
    peria
    -0.70
    Cola
    -0.70
    trop
    -0.67
    ãĥ©ãĥ³
    -0.65
    secut
    -0.65
    incarn
    -0.65
    cean
    -0.64
    POSITIVE LOGITS
    rooms
    1.08
    room
    0.98
     meetings
    0.96
     session
    0.90
     convened
    0.88
     attendees
    0.87
     halls
    0.86
     sessions
    0.86
     Minutes
    0.86
     chaired
    0.84
    Activations Density 11.908%

    No Known Activations