© 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. 35747
    Prev
    Next
    INDEX
    Explanations

    phrases related to software code validation and testing

    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
    26
    +0.10
    0.6%
    459
    +0.09
    0.6%
    679
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.21
    724
    +0.09
    0.14
    326
    +0.09
    0.20
    Negative Logits
    eworld
    -0.65
    emade
    -0.59
    é¾įåĸļ士
    -0.59
    bestos
    -0.58
    bill
    -0.56
    uld
    -0.55
    Æ
    -0.54
    ewater
    -0.53
    izoph
    -0.53
    apter
    -0.53
    POSITIVE LOGITS
     validation
    0.62
     ratings
    0.54
     Jarrett
    0.52
     judgement
    0.51
    Crit
    0.51
     Bryan
    0.50
    hurst
    0.50
     guiActiveUnfocused
    0.49
    rador
    0.49
    orously
    0.49
    Activations Density 7.319%

    No Known Activations