© 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. 12355
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations

    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
    68
    +0.17
    0.6%
    99
    +0.16
    0.5%
    242
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    751
    +0.17
    0.05
    553
    +0.16
    0.04
    323
    +0.14
    0.04
    Negative Logits
    nery
    -1.06
    FORE
    -0.91
     Niet
    -0.90
    etsk
    -0.90
    ysis
    -0.89
     PROGRAM
    -0.88
    zel
    -0.88
    oka
    -0.84
    etic
    -0.84
    nas
    -0.83
    POSITIVE LOGITS
    roads
    1.31
    urst
    1.17
    lines
    1.10
    stocks
    1.03
    arm
    1.02
    Ĥª
    1.00
    atform
    1.00
    arrow
    0.99
    ages
    0.98
    atcher
    0.97
    Activations Density 0.573%

    No Known Activations