© 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 Local
    5. 6-RES_SCL-AJT
    6. 33922
    Prev
    Next
    INDEX
    Explanations

    website URLs and instructions for interacting with them

    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
    67
    +0.06
    0.4%
    566
    +0.06
    0.4%
    417
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.06
    -0.03
    90
    +0.06
    0.06
    767
    +0.05
    0.05
    Negative Logits
    ican
    -0.52
    clinton
    -0.50
    Magikarp
    -0.47
    ster
    -0.46
    ãĤ°
    -0.46
    mite
    -0.45
    blast
    -0.44
    mast
    -0.44
    naissance
    -0.44
    tis
    -0.43
    POSITIVE LOGITS
    onduct
    0.48
    ustain
    0.47
    inct
    0.45
    osponsors
    0.43
    legraph
    0.43
    urities
    0.43
    redits
    0.42
    rouch
    0.42
    urity
    0.41
    urrent
    0.41
    Activations Density 4.844%

    No Known Activations