Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4276
    Prev
    Next
    INDEX
    Explanations

    information related to GPS technology and devices that use GPS connectivity

    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
    +0.18
    1.0%
    326
    +0.14
    0.8%
    538
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.20
    288
    +0.14
    0.18
    698
    +0.09
    0.06
    Negative Logits
    anqu
    -0.76
    isher
    -0.72
    aji
    -0.71
    icum
    -0.70
    ordial
    -0.68
    anza
    -0.67
    ivari
    -0.66
    ality
    -0.64
    itia
    -0.64
    ews
    -0.63
    POSITIVE LOGITS
     coordinates
    0.75
     antenna
    0.73
     transmitter
    0.66
     navigation
    0.65
     GPS
    0.62
     decoding
    0.61
     antennas
    0.61
     tracking
    0.60
     Tracking
    0.59
     spoof
    0.59
    Activations Density 7.009%

    No Known Activations