© 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. 46046
    Prev
    Next
    INDEX
    Explanations

    words related to selecting or choosing options in a digital interface

    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
    0.7%
    288
    +0.12
    0.5%
    583
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    485
    +0.16
    0.07
    726
    +0.12
    0.06
    311
    +0.11
    -0.03
    Negative Logits
    STD
    -0.74
    chief
    -0.71
    von
    -0.69
    amia
    -0.67
    oil
    -0.67
    amen
    -0.66
    orah
    -0.66
    vous
    -0.66
    WARN
    -0.66
    aced
    -0.66
    POSITIVE LOGITS
    ivity
    1.28
    ively
    1.16
    ives
    0.92
    ivities
    0.82
    prising
    0.81
    inations
    0.80
    iveness
    0.80
    axe
    0.78
    ions
    0.77
    ive
    0.76
    Activations Density 4.808%

    No Known Activations