© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14565
    Prev
    Next
    INDEX
    Explanations

    information related to specific locations and events

    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
    640
    +0.16
    0.6%
    627
    +0.15
    0.5%
    430
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.16
    0.06
    627
    +0.15
    0.05
    373
    +0.14
    -0.03
    Negative Logits
    auga
    -0.99
     overw
    -0.87
    ught
    -0.87
    unia
    -0.87
     Bung
    -0.87
     bushes
    -0.86
     lob
    -0.86
     multiplication
    -0.86
     curls
    -0.85
     plots
    -0.84
    POSITIVE LOGITS
    CONT
    1.25
    Thom
    1.19
    EVA
    1.16
    WW
    1.13
    Jer
    1.11
    BUS
    1.09
    via
    1.08
    Phys
    1.05
    VIEW
    1.04
    ENG
    1.04
    Activations Density 0.385%

    No Known Activations