© 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. 3895
    Prev
    Next
    INDEX
    Explanations

    legal terms and names related to legal professionals like lawyers, judges, clients, and attorneys

    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
    +0.23
    1.0%
    679
    +0.15
    0.6%
    571
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.23
    0.09
    679
    +0.15
    0.15
    533
    +0.12
    0.09
    Negative Logits
    plings
    -0.86
     Reincarn
    -0.82
    oppers
    -0.82
    auri
    -0.79
    obyl
    -0.74
    phal
    -0.73
    bows
    -0.73
    omatic
    -0.72
    efully
    -0.71
    ptions
    -0.71
    POSITIVE LOGITS
     Gloria
    0.92
    maid
    0.90
     warr
    0.88
     specializing
    0.87
    yer
    0.87
    suit
    0.85
    yers
    0.84
    suits
    0.84
     solicitor
    0.83
     examiner
    0.79
    Activations Density 7.183%

    No Known Activations