© 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. 35756
    Prev
    Next
    INDEX
    Explanations

    words related to technical settings and adjustments in software and hardware configurations

    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
    1.3%
    575
    +0.12
    0.6%
    288
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.26
    0.30
    255
    +0.12
    0.13
    745
    +0.11
    -0.17
    Negative Logits
    iterator
    -0.71
    女
    -0.70
    ston
    -0.69
    past
    -0.66
    nesses
    -0.66
    LI
    -0.66
    emic
    -0.66
    enary
    -0.65
    lihood
    -0.65
    INESS
    -0.64
    POSITIVE LOGITS
     settings
    0.92
     knob
    0.76
    settings
    0.73
     Settings
    0.73
     tweaks
    0.72
     tweak
    0.72
     menu
    0.70
     Preferences
    0.70
     drawer
    0.67
     Menu
    0.66
    Activations Density 13.140%

    No Known Activations