© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36222
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS code snippets, particularly related to styling and formatting

    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
    550
    +0.10
    0.5%
    96
    +0.10
    0.4%
    164
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.18
    640
    +0.10
    0.16
    289
    +0.10
    -0.01
    Negative Logits
    rine
    -0.90
    SPONSORED
    -0.83
    efficients
    -0.82
    rodu
    -0.79
    ymph
    -0.79
    ieu
    -0.79
    renheit
    -0.79
    orea
    -0.75
    hao
    -0.75
    ĵĺ
    -0.74
    POSITIVE LOGITS
     $_
    0.90
     undefined
    0.80
     })
    0.80
     guiActive
    0.78
    =>
    0.75
     {}
    0.75
     });
    0.75
     Mandatory
    0.74
     ])
    0.73
     @@
    0.72
    Activations Density 6.096%

    No Known Activations