Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 480
    Prev
    Next
    INDEX
    Explanations

    countries of the world or related terms

    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
    742
    +0.04
    0.4%
    504
    +0.04
    0.4%
    121
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    730
    +0.04
    0.01
    692
    +0.04
    0.00
    336
    +0.03
    0.00
    Negative Logits
    bags
    -0.30
    manship
    -0.29
    plex
    -0.26
    rient
    -0.26
    poke
    -0.26
     Clause
    -0.26
    stration
    -0.25
    dig
    -0.25
    âĹ¼
    -0.25
    tes
    -0.25
    POSITIVE LOGITS
    ©¶æ¥µ
    0.27
    ilan
    0.26
    TN
    0.26
    isSpecialOrderable
    0.25
    ModLoader
    0.25
    KS
    0.24
     elders
    0.24
    orthern
    0.24
    Prev
    0.23
     Alb
    0.23
    Activations Density 0.002%

    No Known Activations