© 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 Local
    9. 6-RES_SCL-AJT
    11. 13166
    Prev
    Next
    INDEX
    Explanations

    specific mentions of companies like Uber and Facebook, legal terms related to judicial procedures, and technical details related to computer hardware

    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
    +0.30
    1.3%
    476
    +0.14
    0.6%
    412
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.30
    0.36
    476
    +0.14
    0.06
    412
    +0.12
    0.13
    Negative Logits
    Cause
    -0.66
    ril
    -0.61
    oops
    -0.57
    WF
    -0.57
    ————————————————
    -0.57
    cause
    -0.56
     loudly
    -0.54
     pity
    -0.54
     è£ı
    -0.53
    oshenko
    -0.53
    POSITIVE LOGITS
    ç¥ŀ
    0.62
    design
    0.62
    eous
    0.61
    ipel
    0.61
    :]
    0.59
    lance
    0.58
    abad
    0.57
    occupied
    0.55
     meanwhile
    0.54
     analogy
    0.54
    Activations Density 24.445%

    No Known Activations