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. 5461
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "arise" and its variations

    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
    195
    +0.13
    0.8%
    739
    +0.09
    0.5%
    427
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.13
    0.01
    692
    +0.09
    0.01
    665
    +0.08
    0.02
    Negative Logits
     skelet
    -0.60
    aughed
    -0.56
    lain
    -0.56
    ritch
    -0.55
     frontier
    -0.53
    oried
    -0.52
     Tycoon
    -0.52
     Rangers
    -0.50
    erness
    -0.49
    orate
    -0.48
    POSITIVE LOGITS
     arising
    0.73
     arises
    0.68
     arose
    0.63
    ItemTracker
    0.63
     stoked
    0.59
     spontaneously
    0.58
     arise
    0.55
    ignt
    0.53
     misunder
    0.53
     inconven
    0.53
    Activations Density 0.039%

    No Known Activations