© 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. 40456
    Prev
    Next
    INDEX
    Explanations

    references to national flags

    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
    288
    +0.20
    0.8%
    447
    +0.18
    0.8%
    603
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.17
    129
    +0.18
    0.06
    346
    +0.12
    0.07
    Negative Logits
    nesota
    -0.88
    axter
    -0.80
    lihood
    -0.80
    elsen
    -0.80
    女
    -0.79
    nder
    -0.78
    arios
    -0.77
     subsequ
    -0.76
    soever
    -0.75
    theless
    -0.75
    POSITIVE LOGITS
    pole
    1.38
    ging
    1.33
    rant
    1.27
    staff
    1.22
     bearer
    1.02
    inating
    0.99
    ged
    0.95
    ribute
    0.87
     waving
    0.84
    rants
    0.84
    Activations Density 5.291%

    No Known Activations