© 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. 34797
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics, military operations, and historical events

    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
    481
    +0.24
    1.6%
    373
    +0.23
    1.5%
    211
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.24
    0.23
    481
    +0.23
    0.23
    326
    +0.08
    0.19
    Negative Logits
     horm
    -0.46
     glim
    -0.46
     helic
    -0.45
     charism
    -0.45
     Gors
    -0.43
     cryst
    -0.42
     rul
    -0.41
    Font
    -0.41
     Siber
    -0.41
     caut
    -0.41
    POSITIVE LOGITS
     lasted
    0.47
    imity
    0.45
     simultaneously
    0.45
     celebrated
    0.44
     involving
    0.44
     successfully
    0.43
     perv
    0.43
    ãĤĴ
    0.43
     reverber
    0.41
     relating
    0.41
    Activations Density 5.671%

    No Known Activations