© 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. 14591
    Prev
    Next
    INDEX
    Explanations

    terms related to social welfare programs and benefits, particularly focusing on welfare support, assistance, and resources

    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
    288
    +0.30
    0.9%
    679
    +0.16
    0.5%
    121
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.30
    0.11
    575
    +0.16
    0.08
    444
    +0.14
    0.05
    Negative Logits
    ãĥ£
    -1.11
     ancest
    -0.96
     VIEW
    -0.96
    Sensor
    -0.92
    heter
    -0.91
     Beard
    -0.90
    âĸ¬
    -0.87
    ross
    -0.86
     Sie
    -0.84
    UES
    -0.84
    POSITIVE LOGITS
    fully
    1.21
    fulness
    1.19
    elfare
    1.17
    giving
    1.17
     parole
    1.12
    ocratic
    1.06
    ocrats
    1.05
     counselors
    1.04
     recipients
    1.04
    ful
    1.03
    Activations Density 1.099%

    No Known Activations