© 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. 7553
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases, possibly related to products or technical specifications

    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
    +0.33
    1.5%
    362
    +0.20
    0.9%
    669
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.33
    0.20
    393
    +0.20
    0.14
    636
    +0.14
    0.11
    Negative Logits
    uncle
    -0.89
    ospons
    -0.85
    iard
    -0.80
    clone
    -0.79
     Cosponsors
    -0.79
    aroo
    -0.77
    racuse
    -0.76
    antine
    -0.76
    berus
    -0.75
    ancial
    -0.75
    POSITIVE LOGITS
     equation
    1.01
     bounds
    0.94
     gate
    0.92
     aforementioned
    0.92
     proverbial
    0.92
     earliest
    0.91
     jaws
    0.88
     door
    0.88
     usual
    0.86
     closet
    0.85
    Activations Density 2.043%

    No Known Activations