© 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. 40635
    Prev
    Next
    INDEX
    Explanations

    phrases related to barriers or hindrances

    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
    1.0%
    288
    +0.17
    0.8%
    247
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.21
    0.04
    268
    +0.17
    0.02
    289
    +0.12
    -0.03
    Negative Logits
    ivery
    -0.80
    phis
    -0.74
    ergy
    -0.72
    ammad
    -0.70
    orp
    -0.68
    imbabwe
    -0.67
    ribution
    -0.66
    ories
    -0.66
     largeDownload
    -0.65
    irtual
    -0.64
    POSITIVE LOGITS
     barriers
    1.09
     barrier
    0.97
     erected
    0.88
     separating
    0.86
     walls
    0.77
    buster
    0.77
     crossings
    0.77
     Walls
    0.74
     obstacles
    0.72
    Stone
    0.69
    Activations Density 7.257%

    No Known Activations