© 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. 12929
    Prev
    Next
    INDEX
    Explanations

    mentions of specific parks

    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
    459
    +0.19
    0.6%
    575
    +0.19
    0.6%
    288
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.07
    575
    +0.19
    0.06
    459
    +0.18
    0.05
    Negative Logits
     dilig
    -1.43
    nces
    -1.37
    bestos
    -1.04
    minded
    -1.04
    apter
    -1.03
     pneum
    -1.01
     iod
    -1.00
    Downloadha
    -0.99
    acist
    -0.98
    rontal
    -0.97
    POSITIVE LOGITS
    hurst
    1.48
    walking
    1.33
    park
    1.32
     Zoo
    1.17
    walk
    1.17
    walker
    1.14
    conservancy
    1.10
    lands
    1.10
    stead
    1.10
    erville
    1.08
    Activations Density 0.937%

    No Known Activations