© 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. 34855
    Prev
    Next
    INDEX
    Explanations

    terms related to abstract concepts and theories

    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
    +0.21
    1.0%
    288
    +0.13
    0.6%
    642
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.21
    0.16
    255
    +0.13
    0.09
    211
    +0.11
    -0.01
    Negative Logits
    cffff
    -0.67
    deen
    -0.64
     Peninsula
    -0.62
    GBT
    -0.60
    olla
    -0.59
    ieri
    -0.59
    har
    -0.57
    hiro
    -0.57
     Silence
    -0.57
    bye
    -0.56
    POSITIVE LOGITS
    ually
    1.52
    ual
    1.02
    uality
    0.84
    ical
    0.81
    ional
    0.80
    matically
    0.80
    SHIP
    0.78
    icals
    0.76
    matic
    0.75
    hetically
    0.75
    Activations Density 8.158%

    No Known Activations