Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4529
    Prev
    Next
    INDEX
    Explanations

    medical terms and procedures, legal terms related to criminal charges, and terms related to genetic and environmental factors in relation to criminality and house ownership

    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
    276
    +0.16
    0.7%
    223
    +0.12
    0.5%
    248
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.18
    276
    +0.12
    0.12
    575
    +0.12
    0.13
    Negative Logits
    shapeshifter
    -0.72
    cule
    -0.71
     fingerprints
    -0.71
    HCR
    -0.70
    ++++++++++++++++
    -0.69
     GOODMAN
    -0.68
    lift
    -0.67
    footed
    -0.67
    rawdownloadcloneembedreportprint
    -0.66
     Dickens
    -0.66
    POSITIVE LOGITS
    nostic
    1.36
    nosis
    1.19
    rade
    1.06
    eny
    1.02
     prog
    1.01
    ceed
    1.00
    etric
    0.98
    ulations
    0.94
    rog
    0.91
    ulates
    0.88
    Activations Density 5.249%

    No Known Activations