© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 12672
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software or programming

    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
    447
    +0.20
    0.7%
    38
    +0.13
    0.5%
    145
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.20
    0.09
    696
    +0.13
    0.07
    145
    +0.11
    0.05
    Negative Logits
    è¦ļéĨĴ
    -1.19
    ãĤ¨ãĥ«
    -1.11
     corrid
    -1.11
    ÃŃn
    -1.07
    Ãį
    -1.07
    çͰ
    -1.06
    inous
    -1.02
    utenberg
    -0.98
    án
    -0.98
    é¾įå
    -0.95
    POSITIVE LOGITS
     Idle
    0.90
     Holt
    0.82
     float
    0.81
     Industrial
    0.81
     Gre
    0.80
     Merry
    0.79
     Lim
    0.79
     Rate
    0.78
     Rig
    0.78
     Scroll
    0.78
    Activations Density 1.099%

    No Known Activations