© 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. 14180
    Prev
    Next
    INDEX
    Explanations

    names related to Jewish descent

    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
    491
    +0.09
    0.6%
    590
    +0.08
    0.5%
    23
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.24
    326
    +0.08
    0.21
    590
    +0.08
    0.06
    Negative Logits
    uncture
    -0.51
    istry
    -0.49
    wright
    -0.49
    hair
    -0.48
    utical
    -0.48
    ridges
    -0.48
    lene
    -0.47
    ducers
    -0.46
    antic
    -0.46
    caster
    -0.46
    POSITIVE LOGITS
    ================================================================
    0.47
    iatus
    0.46
     sclerosis
    0.46
     Recovery
    0.45
     Lans
    0.42
     Dwarf
    0.42
    baum
    0.41
    TAIN
    0.40
    Org
    0.39
     Hercules
    0.39
    Activations Density 6.532%

    No Known Activations