© 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. 4713
    Prev
    Next
    INDEX
    Explanations

    mentions of people and their personal stories

    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
    +0.28
    1.5%
    511
    +0.10
    0.5%
    481
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.28
    0.22
    232
    +0.10
    0.18
    511
    +0.09
    0.17
    Negative Logits
    SPONSORED
    -0.61
     thereof
    -0.58
     respectively
    -0.58
     destro
    -0.56
     thereto
    -0.51
     welf
    -0.50
     sacrific
    -0.49
     arrang
    -0.49
     surv
    -0.48
     every
    -0.48
    POSITIVE LOGITS
     Profile
    0.87
     âĵĺ
    0.65
     Edit
    0.64
    ':
    0.59
    iasis
    0.56
    utsu
    0.56
    udos
    0.56
     Plot
    0.56
     Rating
    0.55
    jam
    0.53
    Activations Density 19.829%

    No Known Activations