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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 39997
    Prev
    Next
    INDEX
    Explanations

    technical terms and acronyms related to computer hardware and software

    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
    549
    +0.09
    0.7%
    7
    +0.07
    0.6%
    216
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.09
    0.01
    362
    +0.07
    0.08
    213
    +0.06
    0.04
    Negative Logits
    vous
    -0.43
    tons
    -0.42
    bern
    -0.40
    chart
    -0.38
     Mercury
    -0.37
    ï¸ı
    -0.37
     Wond
    -0.36
    cat
    -0.35
    ï¸
    -0.35
    assetsadobe
    -0.35
    POSITIVE LOGITS
    ILY
    0.67
    MY
    0.62
    RY
    0.60
    RAG
    0.57
    INGS
    0.56
    LY
    0.55
    RR
    0.55
    IES
    0.55
    REL
    0.55
    IFIED
    0.55
    Activations Density 8.749%

    No Known Activations