© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 Local
    9. 6-RES_SCL-AJT
    11. 45962
    Prev
    Next
    INDEX
    Explanations

    word sequences related to apartments or buildings

    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
    +0.24
    1.2%
    167
    +0.12
    0.6%
    270
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.24
    0.04
    551
    +0.12
    0.06
    159
    +0.12
    0.06
    Negative Logits
    Downloadha
    -0.85
    vous
    -0.84
    à¥
    -0.80
    ¶ħ
    -0.80
    ²¾
    -0.79
    ा
    -0.77
    nir
    -0.75
    SPONSORED
    -0.70
    xon
    -0.69
    xtap
    -0.69
    POSITIVE LOGITS
     complexes
    0.97
     apartment
    0.97
     balcony
    0.96
     apartments
    0.92
     buildings
    0.85
     balcon
    0.84
     Dwell
    0.84
     dwellings
    0.82
     rentals
    0.81
     furniture
    0.78
    Activations Density 8.177%

    No Known Activations