© 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 Local
    9. 6-RES_SCL-AJT
    11. 35000
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms related to legal proceedings and financial markets

    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
    +0.14
    0.7%
    232
    +0.10
    0.5%
    124
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.27
    232
    +0.10
    0.12
    585
    +0.09
    0.15
    Negative Logits
    omever
    -0.67
     hepat
    -0.61
     guid
    -0.61
     gren
    -0.60
     crane
    -0.60
     infl
    -0.60
     pressure
    -0.60
     observ
    -0.59
     overtime
    -0.58
     popul
    -0.58
    POSITIVE LOGITS
     Away
    0.97
     Affect
    0.96
     Relationship
    0.94
     Own
    0.93
     Purpose
    0.90
     Architect
    0.90
     Clause
    0.88
     Stupid
    0.88
     Disorder
    0.85
     Shots
    0.85
    Activations Density 12.518%

    No Known Activations