© 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. 14314
    Prev
    Next
    INDEX
    Explanations

    phrases related to characteristics and traits that are important for a particular context

    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
    400
    +0.11
    0.7%
    78
    +0.08
    0.5%
    331
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    191
    +0.11
    0.07
    408
    +0.08
    0.14
    748
    +0.08
    0.05
    Negative Logits
     Expend
    -0.58
    ongo
    -0.57
    iffe
    -0.54
    EE
    -0.52
    MQ
    -0.49
    opa
    -0.49
    igh
    -0.48
    olon
    -0.47
    IRE
    -0.47
    ong
    -0.47
    POSITIVE LOGITS
     requisite
    0.76
    requisites
    0.68
    ptions
    0.64
     necessary
    0.64
    apon
    0.60
    ãĤ¤ãĥĪ
    0.60
    liest
    0.58
    oufl
    0.57
     feat
    0.55
     prerequisite
    0.55
    Activations Density 8.490%

    No Known Activations