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 L0 E2E Recon
    5. 2-RES_SLEFR-AJT
    6. 5368
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "precious."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_slefr-ajt/2-res_slefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    730
    +0.10
    0.6%
    146
    +0.09
    0.5%
    30
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    730
    +0.10
    0.01
    370
    +0.09
    0.01
    139
    +0.09
    0.01
    Negative Logits
     Strauss
    -0.54
    _-
    -0.54
    nih
    -0.54
     Dempsey
    -0.52
    LINE
    -0.50
    RESULTS
    -0.50
     Frazier
    -0.50
     pitched
    -0.49
     indic
    -0.49
    RAFT
    -0.49
    POSITIVE LOGITS
     precious
    0.72
     metals
    0.67
    ulously
    0.66
    tery
    0.59
    ness
    0.59
    ulous
    0.56
    izards
    0.55
    sea
    0.52
    opolis
    0.50
     Dragonbound
    0.50
    Activations Density 0.008%

    No Known Activations