© 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. 40476
    Prev
    Next
    INDEX
    Explanations

    phrases related to location or movement of people

    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
    +0.16
    0.7%
    58
    +0.12
    0.5%
    129
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.16
    0.23
    608
    +0.12
    0.17
    362
    +0.12
    0.12
    Negative Logits
    adding
    -0.73
    inion
    -0.70
    requisite
    -0.70
     agric
    -0.69
    stead
    -0.68
    EStreamFrame
    -0.68
    trap
    -0.67
    currency
    -0.66
     whistle
    -0.65
    prime
    -0.65
    POSITIVE LOGITS
    dust
    1.02
    lights
    0.97
     eye
    0.86
    tein
    0.79
     Eye
    0.79
     firsthand
    0.78
     daylight
    0.78
    URES
    0.77
     fit
    0.76
    awed
    0.75
    Activations Density 10.131%

    No Known Activations