© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3415
    Prev
    Next
    INDEX
    Explanations

    abstract concepts, technical terms, and possibly legal or academic terminology

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    680
    +0.11
    0.5%
    767
    +0.11
    0.5%
    139
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.11
    0.02
    373
    +0.11
    -0.01
    299
    +0.10
    0.02
    Negative Logits
    igi
    -0.92
    ardless
    -0.87
    icans
    -0.81
    artz
    -0.78
    amo
    -0.78
    grave
    -0.76
    ofi
    -0.75
    borgh
    -0.74
    rikes
    -0.73
    ican
    -0.73
    POSITIVE LOGITS
     QUEST
    0.81
    ATIONAL
    0.77
     STORY
    0.74
    SHIP
    0.73
     ISIL
    0.69
     NEWS
    0.67
     CHRIST
    0.67
    ATION
    0.66
    =-=-=-=-
    0.66
     PLAN
    0.66
    Activations Density 0.114%

    No Known Activations