© 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 Local
    5. 6-RES_SCL-AJT
    6. 4782
    Prev
    Next
    INDEX
    Explanations

    references to forests, deforestation, and related environmental issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.22
    1.0%
    288
    +0.20
    0.9%
    326
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.17
    575
    +0.20
    0.12
    326
    +0.11
    0.15
    Negative Logits
    Magikarp
    -0.75
    HK
    -0.72
    OPLE
    -0.71
    enger
    -0.71
    soever
    -0.71
    realDonaldTrump
    -0.69
    uberty
    -0.69
    Reason
    -0.67
     neurot
    -0.65
    Wilson
    -0.65
    POSITIVE LOGITS
    lands
    0.96
    forest
    0.91
    lake
    0.90
     canopy
    0.87
    bank
    0.82
    land
    0.82
    ãĤ¼ãĤ¦ãĤ¹
    0.82
     forests
    0.81
    orde
    0.81
     forest
    0.80
    Activations Density 4.690%

    No Known Activations