© 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. 14202
    Prev
    Next
    INDEX
    Explanations

    names of American football players

    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
    588
    +0.05
    0.5%
    638
    +0.05
    0.5%
    272
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.05
    0.10
    525
    +0.05
    0.06
    103
    +0.05
    0.07
    Negative Logits
    culosis
    -0.39
     Zimbabwe
    -0.36
     Bullets
    -0.33
     Boko
    -0.33
     Qiao
    -0.32
    ashtra
    -0.32
     crocod
    -0.32
     Mub
    -0.32
     Creed
    -0.32
     Assy
    -0.30
    POSITIVE LOGITS
    alk
    0.36
    ourke
    0.36
    Sleep
    0.35
    apps
    0.34
    Flo
    0.34
    flo
    0.34
    acles
    0.34
    aman
    0.34
    doi
    0.34
    anan
    0.34
    Activations Density 0.463%

    No Known Activations