© 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 1493
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court outcomes

    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
    153
    +0.07
    0.5%
    356
    +0.07
    0.5%
    585
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.07
    0.04
    151
    +0.07
    0.05
    668
    +0.06
    0.03
    Negative Logits
    enf
    -0.45
    arling
    -0.42
    oppy
    -0.42
    raltar
    -0.41
    emetery
    -0.41
    creation
    -0.40
    hare
    -0.40
     lear
    -0.39
    Bloom
    -0.39
    ppa
    -0.39
    POSITIVE LOGITS
     exoner
    0.51
    lect
    0.50
     indict
    0.47
    ittal
    0.45
     verdict
    0.44
    proof
    0.41
    uries
    0.41
     Ig
    0.40
     Tot
    0.40
     unanimously
    0.39
    Activations Density 0.389%

    No Known Activations