© 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. 46049
    Prev
    Next
    INDEX
    Explanations

    negative phrases or statements

    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
    +0.11
    0.8%
    642
    +0.07
    0.5%
    551
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.11
    0.08
    643
    +0.07
    0.05
    356
    +0.07
    0.01
    Negative Logits
    soDeliveryDate
    -0.44
    quickShipAvailable
    -0.44
    æĸ¹
    -0.41
     Shot
    -0.41
    interstitial
    -0.40
     Gone
    -0.39
     Called
    -0.38
     Guys
    -0.38
    ME
    -0.38
     Mant
    -0.38
    POSITIVE LOGITS
     afford
    0.66
     adequately
    0.61
     satisf
    0.59
     foresee
    0.59
     tolerate
    0.58
     withstand
    0.57
     distinguish
    0.55
     convince
    0.55
     comprehend
    0.55
    icably
    0.54
    Activations Density 8.999%

    No Known Activations