© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3817
    Prev
    Next
    INDEX
    Explanations

    references to historical events, political figures, and international relations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.15
    0.5%
    264
    +0.14
    0.5%
    210
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.14
    210
    +0.14
    0.07
    556
    +0.13
    0.08
    Negative Logits
    icter
    -0.97
    oscope
    -0.97
    emet
    -0.91
    effic
    -0.87
    İĭ
    -0.85
    udeb
    -0.83
    BILITIES
    -0.82
    orks
    -0.82
    GGGGGGGG
    -0.81
    aida
    -0.80
    POSITIVE LOGITS
    tenance
    1.07
     alike
    1.02
     hybrid
    0.97
     complexes
    0.96
     hybrids
    0.96
    byter
    0.95
    osterone
    0.95
     Relations
    0.88
    âĦ¢:
    0.87
    ption
    0.86
    Activations Density 2.949%

    No Known Activations