© 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. 6740
    Prev
    Next
    INDEX
    Explanations

    and highlight specific sentences from longer texts

    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
    +0.29
    1.0%
    217
    +0.15
    0.5%
    720
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.29
    0.09
    546
    +0.15
    0.08
    356
    +0.14
    0.05
    Negative Logits
    interstitial
    -1.02
    gow
    -0.85
    asons
    -0.85
    ãĤ¶
    -0.84
    ãĤ´ãĥ³
    -0.84
    è¦ļéĨĴ
    -0.83
    ORPG
    -0.83
    Ô
    -0.83
    nexus
    -0.80
    ctive
    -0.79
    POSITIVE LOGITS
     alas
    1.38
     yes
    1.23
     although
    1.17
     uh
    1.16
     um
    1.12
     yeah
    1.12
     unfortunately
    1.06
     despite
    1.05
     thankfully
    1.03
     sadly
    1.03
    Activations Density 1.528%

    No Known Activations