© 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. 4066
    Prev
    Next
    INDEX
    Explanations

    information about different government policies and economic factors

    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
    +0.27
    1.9%
    393
    +0.14
    0.9%
    43
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.27
    0.33
    546
    +0.14
    0.18
    721
    +0.07
    0.15
    Negative Logits
    soDeliveryDate
    -0.48
    MJ
    -0.44
    orn
    -0.42
    WithNo
    -0.42
    leground
    -0.41
    IFIED
    -0.40
    oph
    -0.40
    blank
    -0.40
    ãĤĬ
    -0.40
    nai
    -0.40
    POSITIVE LOGITS
     however
    0.54
     coupled
    0.50
     moreover
    0.48
     actionGroup
    0.45
    dos
    0.45
     please
    0.44
     minimizing
    0.43
    iencies
    0.42
     whereby
    0.42
    phasis
    0.42
    Activations Density 14.620%

    No Known Activations