© 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 Local
    9. 6-RES_SCL-AJT
    11. 35302
    Prev
    Next
    INDEX
    Explanations

    common terms related to centers or central points

    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
    447
    +0.10
    0.6%
    99
    +0.10
    0.6%
    421
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.21
    1
    +0.10
    0.10
    724
    +0.09
    0.14
    Negative Logits
    jee
    -0.60
    thur
    -0.59
    hib
    -0.55
    axe
    -0.54
    quet
    -0.54
    gotten
    -0.53
    ãĤī
    -0.52
    ht
    -0.51
    hy
    -0.50
    andro
    -0.49
    POSITIVE LOGITS
    SHIP
    0.56
     centered
    0.56
     around
    0.56
    cius
    0.51
    urrency
    0.51
    rikes
    0.51
    PIN
    0.51
     Revel
    0.50
    rike
    0.49
    icago
    0.49
    Activations Density 7.484%

    No Known Activations