© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6300
    Prev
    Next
    INDEX
    Explanations

    phrases related to successfully completing or achieving something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    393
    +0.25
    0.8%
    651
    +0.14
    0.5%
    202
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.25
    0.09
    259
    +0.14
    0.07
    689
    +0.14
    0.08
    Negative Logits
    ãĥ©ãĥ³
    -0.97
    hips
    -0.90
    Texture
    -0.83
    Priv
    -0.80
    idth
    -0.80
    ãĥ«
    -0.80
    »
    -0.79
    ²
    -0.79
    į
    -0.79
     combatants
    -0.78
    POSITIVE LOGITS
    alian
    1.63
    chy
    1.62
    unes
    1.57
    self
    1.21
    ueller
    1.18
    iner
    1.18
    asca
    1.11
    atic
    1.10
    alia
    1.10
     boils
    1.03
    Activations Density 1.226%

    No Known Activations