© 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. 3526
    Prev
    Next
    INDEX
    Explanations

    references related to living conditions and housing

    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
    132
    +0.21
    0.7%
    575
    +0.21
    0.7%
    48
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.21
    0.06
    575
    +0.21
    0.05
    353
    +0.14
    0.04
    Negative Logits
    reg
    -1.32
    osen
    -1.21
    pport
    -1.18
    ère
    -1.14
    IFIC
    -1.11
    ername
    -1.10
    aneers
    -1.07
    elight
    -1.06
    uning
    -1.05
    NetMessage
    -1.04
    POSITIVE LOGITS
     Wage
    1.47
     wage
    1.30
    lihood
    1.30
    hart
    1.19
     liv
    1.14
    ths
    1.14
     quarters
    1.11
    liest
    1.09
    living
    1.07
    lor
    1.06
    Activations Density 0.565%

    No Known Activations