© 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. 39928
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal rights and civil liberties

    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
    447
    +0.26
    1.1%
    218
    +0.14
    0.6%
    679
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.26
    0.06
    253
    +0.14
    0.12
    575
    +0.14
    0.15
    Negative Logits
    -+-+
    -0.71
     Claus
    -0.67
    aco
    -0.67
    intage
    -0.66
    arette
    -0.66
    ãĤ©
    -0.66
    OS
    -0.64
     Sark
    -0.64
    vae
    -0.63
    âĸ¬
    -0.63
    POSITIVE LOGITS
    rights
    1.19
     rights
    1.16
     Rights
    1.04
     freedoms
    0.88
    eous
    0.85
     afforded
    0.85
     protections
    0.84
     conferred
    0.83
     abuses
    0.83
     attorneys
    0.83
    Activations Density 10.053%

    No Known Activations