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. 5390
    Prev
    Next
    INDEX
    Explanations

    the presence of backslashes in various contexts

    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
    127
    +0.10
    0.6%
    661
    +0.09
    0.5%
    282
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.10
    0.04
    578
    +0.09
    0.03
    365
    +0.09
    0.03
    Negative Logits
     killers
    -0.55
     commuting
    -0.55
     coping
    -0.54
     sacr
    -0.53
     fundamentals
    -0.53
     murderers
    -0.52
     punishing
    -0.52
     regulated
    -0.51
     prosecutions
    -0.50
     cruc
    -0.49
    POSITIVE LOGITS
    ucci
    0.75
    76561
    0.70
    Els
    0.63
    uously
    0.62
    ues
    0.62
    omial
    0.62
    uin
    0.61
    ãĥķ
    0.60
    oret
    0.60
    ongo
    0.60
    Activations Density 0.014%

    No Known Activations