© 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 3462
    Prev
    Next
    INDEX
    Explanations

    names or words related to the name "George"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.19
    0.7%
    569
    +0.16
    0.6%
    421
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.11
    326
    +0.16
    0.08
    367
    +0.15
    0.07
    Negative Logits
    pled
    -1.02
    footed
    -0.94
    pling
    -0.84
    RED
    -0.83
    ocular
    -0.83
    charge
    -0.83
    Snake
    -0.82
     smoked
    -0.82
    VIS
    -0.82
     chained
    -0.79
    POSITIVE LOGITS
    ians
    1.63
     Prix
    1.24
    IAN
    1.20
    iana
    1.19
    ian
    1.18
    opol
    1.15
    inders
    1.11
    ials
    1.10
    ienne
    1.09
    iate
    1.07
    Activations Density 1.156%

    No Known Activations