© 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. 4616
    Prev
    Next
    INDEX
    Explanations

    terms related to displacement or forced relocation

    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
    651
    +0.12
    0.5%
    339
    +0.12
    0.5%
    746
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    719
    +0.12
    0.09
    721
    +0.12
    0.07
    421
    +0.12
    0.07
    Negative Logits
     Hebdo
    -0.78
    velt
    -0.73
    FactoryReloaded
    -0.72
    NEY
    -0.71
     Breach
    -0.69
    ween
    -0.66
    ++++
    -0.66
    #$
    -0.65
    Ble
    -0.64
     guiActiveUnfocused
    -0.63
    POSITIVE LOGITS
    adic
    1.15
    inates
    1.14
    inally
    1.07
     nom
    1.05
    nom
    1.04
    atis
    1.01
     Nom
    0.96
    ril
    0.93
    ose
    0.93
    inational
    0.92
    Activations Density 7.704%

    No Known Activations