© 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. 33851
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs reflecting self-representation and active participation in different activities

    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
    +0.14
    0.8%
    94
    +0.10
    0.6%
    709
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.14
    578
    +0.10
    0.04
    515
    +0.09
    0.09
    Negative Logits
    ilateral
    -0.51
     Tycoon
    -0.49
    ipl
    -0.46
    onga
    -0.46
     Onion
    -0.45
    brainer
    -0.44
     pige
    -0.43
    imag
    -0.43
    di
    -0.43
     Manufact
    -0.43
    POSITIVE LOGITS
    selves
    0.67
     anew
    0.63
    aces
    0.58
     territ
    0.58
     creatively
    0.55
    DragonMagazine
    0.53
     elsewhere
    0.53
    çĦ
    0.53
    ternally
    0.52
     Bene
    0.51
    Activations Density 8.214%

    No Known Activations