© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 33279
    Prev
    Next
    INDEX
    Explanations

    These activations suggest that the neuron is looking for references to technical procedures and instructions

    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
    284
    +0.08
    0.5%
    336
    +0.08
    0.5%
    606
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    606
    +0.08
    0.10
    663
    +0.08
    0.07
    637
    +0.07
    0.08
    Negative Logits
     ratios
    -0.52
    tein
    -0.50
     Divide
    -0.46
     sinks
    -0.45
    awaru
    -0.44
     scores
    -0.44
    èĢħ
    -0.43
     Corridor
    -0.43
     heights
    -0.43
     pilgrims
    -0.43
    POSITIVE LOGITS
    pport
    0.75
    seless
    0.65
    ccess
    0.64
    Torrent
    0.54
    tv
    0.52
    tymology
    0.51
    inent
    0.51
    xt
    0.51
    ft
    0.50
    lv
    0.50
    Activations Density 4.717%

    No Known Activations