© 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. 34868
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to memory triggers that prompt reflection 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
    +0.17
    0.7%
    326
    +0.11
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.28
    119
    +0.11
    0.13
    248
    +0.11
    0.06
    Negative Logits
    estern
    -0.81
     ILCS
    -0.78
    adesh
    -0.74
    bard
    -0.68
    á
    -0.67
    ccording
    -0.65
     deductible
    -0.64
    abad
    -0.63
     pursuit
    -0.62
     Wikimedia
    -0.60
    POSITIVE LOGITS
    ingly
    1.19
    ĸļ
    1.00
     us
    0.91
     remind
    0.88
    jas
    0.86
    fulness
    0.86
    akeru
    0.83
    isance
    0.81
    ening
    0.80
    ón
    0.76
    Activations Density 10.883%

    No Known Activations