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

    Neuronpedia

    Jacobian LensNEW
    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. 33285
    Prev
    Next
    INDEX
    Explanations

    words related to technology and optimization

    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
    311
    +0.10
    0.6%
    465
    +0.10
    0.6%
    276
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.10
    0.09
    525
    +0.10
    0.10
    232
    +0.09
    0.09
    Negative Logits
    Madison
    -0.61
    llah
    -0.57
    UGH
    -0.57
    è¦ļéĨĴ
    -0.55
     withd
    -0.54
    SHIP
    -0.54
    ptives
    -0.54
     encount
    -0.53
    INESS
    -0.53
    lled
    -0.52
    POSITIVE LOGITS
    imum
    0.98
    imal
    0.93
    icians
    0.78
    ician
    0.78
    imus
    0.76
    icles
    0.76
    ractor
    0.74
    ical
    0.70
    ament
    0.69
    ypes
    0.69
    Activations Density 10.172%

    No Known Activations