© 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
    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. 5600
    Prev
    Next
    INDEX
    Explanations

    locations, such as towns and cities, mentioned in news text

    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
    +0.28
    1.0%
    180
    +0.14
    0.5%
    732
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    611
    +0.28
    0.07
    180
    +0.14
    0.05
    133
    +0.12
    0.05
    Negative Logits
    <?
    -1.01
     showc
    -1.00
     reperto
    -0.95
     appl
    -0.90
     coerc
    -0.89
     pestic
    -0.87
    illance
    -0.85
    advertisement
    -0.85
     conform
    -0.84
    reprene
    -0.84
    POSITIVE LOGITS
     Alb
    0.95
     Dover
    0.93
     Dreams
    0.90
     Mind
    0.90
     Mour
    0.84
     Tir
    0.84
     Giants
    0.83
     Nev
    0.82
     Ascension
    0.82
     Lau
    0.81
    Activations Density 0.556%

    No Known Activations