© 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. 40592
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology servers and their functioning, such as issues, maintenance, and operations

    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
    497
    +0.11
    0.8%
    756
    +0.09
    0.6%
    679
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.19
    114
    +0.09
    0.11
    288
    +0.07
    0.20
    Negative Logits
    lier
    -0.47
    hood
    -0.45
    rous
    -0.41
    âĺħâĺħ
    -0.41
    KNOWN
    -0.41
    lihood
    -0.40
    ãĤī
    -0.40
    football
    -0.39
    itatively
    -0.39
    ned
    -0.38
    POSITIVE LOGITS
    pace
    0.97
    mith
    0.96
    paces
    0.92
    hare
    0.90
    hips
    0.88
    hops
    0.83
    poons
    0.79
    ource
    0.78
    pring
    0.78
    chool
    0.78
    Activations Density 6.738%

    No Known Activations