© 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. 45914
    Prev
    Next
    INDEX
    Explanations

    phrases related to kingdoms and royalty

    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
    +0.12
    0.8%
    288
    +0.10
    0.7%
    97
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.12
    0.10
    288
    +0.10
    0.19
    517
    +0.08
    0.09
    Negative Logits
    CAST
    -0.49
    lder
    -0.49
    pos
    -0.47
    lus
    -0.46
    matter
    -0.46
    eman
    -0.44
    esters
    -0.44
    opian
    -0.44
    inez
    -0.44
    chie
    -0.43
    POSITIVE LOGITS
     Hearts
    0.70
    DOM
    0.67
     Arabian
    0.60
    wide
    0.59
     Arabia
    0.54
     kingdom
    0.52
     Halls
    0.51
    doms
    0.50
     oun
    0.50
    loo
    0.49
    Activations Density 6.835%

    No Known Activations