© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 373
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development processes and beta testing

    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
    +0.20
    0.7%
    524
    +0.14
    0.5%
    500
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.13
    641
    +0.14
    0.09
    651
    +0.13
    0.08
    Negative Logits
    lat
    -0.98
    iasis
    -0.94
    ategories
    -0.92
    die
    -0.92
     traged
    -0.90
     surname
    -0.89
     Mysteries
    -0.88
    riminal
    -0.87
    si
    -0.87
    andra
    -0.85
    POSITIVE LOGITS
     testers
    1.14
     prototypes
    1.10
     testing
    1.07
     prototype
    1.01
    DEM
    1.00
     demo
    1.00
     test
    1.00
     sketches
    0.94
     Prototype
    0.94
     demos
    0.93
    Activations Density 2.571%

    No Known Activations