© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4104
    Prev
    Next
    INDEX
    Explanations

    information related to economics and financial stability

    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
    115
    +0.09
    0.5%
    71
    +0.09
    0.5%
    447
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.09
    0.13
    270
    +0.09
    0.04
    71
    +0.08
    -0.03
    Negative Logits
    atform
    -0.64
    udic
    -0.62
    ulhu
    -0.61
    ĸļ
    -0.56
    ufact
    -0.56
    azeera
    -0.55
    uctor
    -0.53
    iday
    -0.53
    uga
    -0.53
    arij
    -0.51
    POSITIVE LOGITS
    ãĤ¼
    0.60
    onz
    0.60
     welf
    0.58
    thood
    0.56
    tax
    0.56
    intent
    0.55
    Includes
    0.54
     Frenzy
    0.52
     faire
    0.52
    âĨij
    0.50
    Activations Density 26.717%

    No Known Activations