© 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. 14095
    Prev
    Next
    INDEX
    Explanations

    phrases related to inevitability or certainty

    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
    370
    +0.15
    0.7%
    326
    +0.12
    0.6%
    661
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.15
    -0.05
    661
    +0.12
    0.05
    370
    +0.11
    0.06
    Negative Logits
    issance
    -0.91
    soDeliveryDate
    -0.75
     fielded
    -0.75
    amera
    -0.73
    sych
    -0.69
     Avalon
    -0.68
    ciation
    -0.66
    visors
    -0.65
    HAEL
    -0.65
    ptive
    -0.63
    POSITIVE LOGITS
    lessly
    1.12
    less
    1.07
    gling
    0.98
    fold
    0.94
     bound
    0.91
    ging
    0.91
    bound
    0.83
    lessness
    0.83
    binding
    0.82
    naire
    0.81
    Activations Density 7.102%

    No Known Activations