© 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. 14244
    Prev
    Next
    INDEX
    Explanations

    Minecraft-related data entities

    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
    572
    +0.07
    0.6%
    501
    +0.06
    0.4%
    534
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    534
    +0.07
    0.01
    496
    +0.06
    0.01
    728
    +0.05
    0.01
    Negative Logits
    aged
    -0.43
    urg
    -0.40
    aging
    -0.39
     Yaz
    -0.36
    ogram
    -0.36
    xy
    -0.35
     Crew
    -0.35
     squad
    -0.35
    agon
    -0.34
     recovering
    -0.33
    POSITIVE LOGITS
    âĨ
    0.49
    ONSORED
    0.46
    -+-+
    0.45
    ĸļ
    0.43
    !/
    0.43
    Reviewer
    0.43
    \\\\\\\\
    0.43
    ="/
    0.41
    ipedia
    0.40
    âĨij
    0.40
    Activations Density 0.009%

    No Known Activations