© 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
    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. 13850
    Prev
    Next
    INDEX
    Explanations

    words related to Wi-Fi technology and 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
    326
    +0.17
    0.7%
    99
    +0.16
    0.6%
    343
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    649
    +0.17
    0.03
    99
    +0.16
    0.07
    107
    +0.14
    0.03
    Negative Logits
    */(
    -1.06
    uate
    -0.84
    ioned
    -0.83
    lain
    -0.83
    å§«
    -0.82
    orians
    -0.81
    orian
    -0.77
    ions
    -0.71
    ional
    -0.70
     Carbuncle
    -0.70
    POSITIVE LOGITS
    Wi
    1.05
    Fi
    1.02
    omen
    0.98
    Yo
    0.95
    wan
    0.94
    FFER
    0.92
    wi
    0.91
    Pi
    0.89
     Wi
    0.88
    pping
    0.86
    Activations Density 4.180%

    No Known Activations