© 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. 13250
    Prev
    Next
    INDEX
    Explanations

    mentions related to land use and management

    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
    +0.27
    0.9%
    76
    +0.16
    0.5%
    570
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.27
    0.08
    76
    +0.16
    0.07
    152
    +0.15
    0.07
    Negative Logits
    vernment
    -1.30
    pload
    -0.94
     Bour
    -0.94
    BY
    -0.92
    ansen
    -0.89
    hift
    -0.88
    asio
    -0.84
    aldo
    -0.83
    eters
    -0.83
     Sisters
    -0.83
    POSITIVE LOGITS
    mine
    1.35
    locked
    1.35
    scape
    1.29
    owner
    1.24
    mass
    1.20
    grave
    1.18
    plane
    1.15
    gra
    1.15
    marks
    1.10
    wright
    1.07
    Activations Density 0.986%

    No Known Activations