© 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. 162
    Prev
    Next
    INDEX
    Explanations

    phrases related to urban development and community planning

    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
    288
    +0.18
    0.7%
    459
    +0.16
    0.6%
    617
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.18
    459
    +0.16
    0.11
    575
    +0.13
    0.11
    Negative Logits
    othal
    -0.91
    reme
    -0.90
    vana
    -0.87
    osi
    -0.87
    yip
    -0.86
    nikov
    -0.85
    iety
    -0.85
    ubi
    -0.84
    bern
    -0.83
    hematic
    -0.81
    POSITIVE LOGITS
     redevelopment
    1.42
     projects
    1.16
     renovation
    1.15
     renovations
    1.15
     construction
    1.12
     bulldo
    1.11
    Construction
    1.10
     buildings
    1.08
     occupancy
    1.06
     park
    1.04
    Activations Density 3.282%

    No Known Activations