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. 5373
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals or groups in a sporting context

    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
    740
    +0.08
    0.5%
    225
    +0.08
    0.5%
    647
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.08
    0.01
    702
    +0.08
    0.01
    611
    +0.08
    0.01
    Negative Logits
    ãĥĩãĤ£
    -0.58
    bh
    -0.55
     Cruz
    -0.55
     Dame
    -0.54
     Atkins
    -0.54
    lust
    -0.53
    anto
    -0.53
     christ
    -0.53
     brood
    -0.53
     veter
    -0.52
    POSITIVE LOGITS
    papers
    0.67
     Bil
    0.65
    Introduced
    0.64
    olin
    0.61
    bit
    0.60
    bits
    0.60
    boa
    0.58
    Ear
    0.57
    obiles
    0.57
    naire
    0.57
    Activations Density 0.005%

    No Known Activations