© 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. 45878
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to intellectual property and innovation

    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
    +0.19
    1.0%
    288
    +0.16
    0.8%
    578
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.18
    568
    +0.16
    0.05
    271
    +0.11
    0.05
    Negative Logits
     Mara
    -0.73
    avers
    -0.70
    drops
    -0.65
    iland
    -0.63
    DAY
    -0.63
    Lago
    -0.63
     Veterinary
    -0.62
    Lt
    -0.61
     Slay
    -0.60
    borg
    -0.60
    POSITIVE LOGITS
    ellectual
    0.94
     dishon
    0.79
     curiosity
    0.76
    igr
    0.72
    itialized
    0.72
    property
    0.71
    itle
    0.68
     underpin
    0.67
     intellectual
    0.67
    minded
    0.67
    Activations Density 5.196%

    No Known Activations