© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13763
    Prev
    Next
    INDEX
    Explanations

    time-related phrases and expressions

    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
    +0.21
    0.9%
    726
    +0.12
    0.5%
    279
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.21
    0.12
    517
    +0.12
    0.07
    698
    +0.12
    0.06
    Negative Logits
    ĪĴ
    -0.90
    agra
    -0.82
    ortium
    -0.74
    dinand
    -0.68
    assis
    -0.67
    Runner
    -0.66
    opol
    -0.66
    omination
    -0.66
    rig
    -0.66
    aleb
    -0.65
    POSITIVE LOGITS
    days
    0.89
     ago
    0.89
     Ago
    0.81
     consuming
    0.81
     ILCS
    0.76
    flies
    0.74
    frames
    0.73
     thereafter
    0.70
     msec
    0.70
     throughout
    0.70
    Activations Density 5.697%

    No Known Activations