© 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. 1784
    Prev
    Next
    INDEX
    Explanations

    locations or buildings within sentences

    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
    +0.33
    1.1%
    611
    +0.16
    0.5%
    362
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.33
    0.11
    476
    +0.16
    0.08
    611
    +0.15
    0.10
    Negative Logits
    Äĩ
    -1.20
    Ô
    -1.14
     Cosponsors
    -1.08
    wcs
    -1.05
    ghai
    -1.02
    uristic
    -0.99
    ÃŁ
    -0.98
    hester
    -0.97
    agy
    -0.97
    ño
    -0.96
    POSITIVE LOGITS
    tnc
    0.96
     darkness
    0.89
     Settlement
    0.88
     each
    0.84
     Gors
    0.83
     scrimmage
    0.83
     course
    0.83
     unsuspecting
    0.82
     Duel
    0.81
     lodge
    0.79
    Activations Density 1.699%

    No Known Activations