© 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. 33437
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning or starting point of a process or action

    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
    +0.12
    0.5%
    86
    +0.11
    0.5%
    320
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.12
    0.08
    665
    +0.11
    0.13
    738
    +0.11
    0.06
    Negative Logits
     wrought
    -0.72
    phy
    -0.69
    quickShipAvailable
    -0.68
    Origin
    -0.67
     entirety
    -0.62
     precincts
    -0.61
     Britann
    -0.60
    pedia
    -0.60
    acho
    -0.59
     mutated
    -0.58
    POSITIVE LOGITS
     anew
    1.04
    ners
    0.79
    ablish
    0.78
    NING
    0.78
    ezvous
    0.76
    nings
    0.76
    igmatic
    0.76
    TAIN
    0.75
    dule
    0.75
    20439
    0.74
    Activations Density 6.675%

    No Known Activations