© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 11041
    Prev
    Next
    INDEX
    Explanations

    measurement units and product listings

    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
    326
    +0.19
    0.7%
    187
    +0.13
    0.4%
    648
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.19
    0.08
    17
    +0.13
    0.05
    23
    +0.13
    0.07
    Negative Logits
     behavi
    -1.07
     lax
    -0.90
     Debor
    -0.88
     fearful
    -0.85
     contrace
    -0.83
     murd
    -0.81
     distressed
    -0.80
     behav
    -0.79
     embargo
    -0.79
    Recomm
    -0.78
    POSITIVE LOGITS
    reens
    1.25
    hz
    1.16
    bps
    1.03
    arten
    1.03
    00
    1.01
    035
    1.01
    ards
    1.00
    ruary
    0.99
    030
    0.99
    imore
    0.98
    Activations Density 1.086%

    No Known Activations