© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5383
    Prev
    Next
    INDEX
    Explanations

    quotes and mentions of accomplishments or abilities in sports

    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
    640
    +0.27
    0.9%
    549
    +0.15
    0.5%
    618
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.27
    0.20
    64
    +0.15
    -0.06
    94
    +0.14
    0.12
    Negative Logits
    obar
    -1.24
    oval
    -1.12
    uno
    -1.07
    opausal
    -1.01
    atra
    -0.99
    avorite
    -0.99
    ijing
    -0.96
    aez
    -0.94
    utical
    -0.94
    heit
    -0.94
    POSITIVE LOGITS
    âĸ¬
    0.99
    poll
    0.97
     Motorsport
    0.94
     Labour
    0.90
    ircraft
    0.87
     htt
    0.87
     Trafford
    0.87
    Poll
    0.87
     Durham
    0.87
     Entry
    0.86
    Activations Density 1.122%

    No Known Activations