© 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 EvalsExportsAPI 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. 33358
    Prev
    Next
    INDEX
    Explanations

    instructions and commands related to software installation and technical setup

    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
    +0.14
    0.7%
    459
    +0.13
    0.7%
    71
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.11
    191
    +0.13
    0.06
    393
    +0.09
    0.22
    Negative Logits
    sem
    -0.67
    mid
    -0.66
    riers
    -0.66
    pee
    -0.63
    eyes
    -0.63
    phy
    -0.61
    uel
    -0.61
    vous
    -0.61
    ĸļ
    -0.60
    irst
    -0.59
    POSITIVE LOGITS
     macOS
    0.70
    strap
    0.70
     uninstall
    0.67
     bund
    0.67
    rom
    0.63
     XCOM
    0.63
     install
    0.63
    wrapper
    0.62
     GNOME
    0.61
     GNU
    0.61
    Activations Density 9.564%

    No Known Activations