© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1579
    Prev
    Next
    INDEX
    Explanations

    Spanish words containing the letter combination "an"

    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
    352
    +0.07
    0.5%
    240
    +0.06
    0.5%
    642
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.07
    0.02
    112
    +0.06
    0.02
    284
    +0.06
    0.02
    Negative Logits
    neum
    -0.44
    utical
    -0.43
    ibles
    -0.42
    imester
    -0.41
    ngth
    -0.41
    atically
    -0.39
     Smy
    -0.39
    senal
    -0.39
    oxin
    -0.38
    Tact
    -0.38
    POSITIVE LOGITS
    ghai
    0.46
    clinton
    0.42
    jar
    0.41
     swings
    0.40
     docking
    0.39
    raising
    0.39
     footing
    0.39
     envelope
    0.38
     upstream
    0.38
    warming
    0.38
    Activations Density 0.027%

    No Known Activations