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. 9878
    Prev
    Next
    INDEX
    Explanations

    terms related to education and educational institutions

    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
    530
    +0.08
    0.5%
    624
    +0.07
    0.5%
    73
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.03
    575
    +0.07
    0.02
    653
    +0.07
    0.02
    Negative Logits
    aron
    -0.53
     McCull
    -0.53
    eur
    -0.53
    rology
    -0.51
    rons
    -0.51
    rice
    -0.49
     Leilan
    -0.48
    chal
    -0.48
     Lord
    -0.47
    oning
    -0.47
    POSITIVE LOGITS
    mercial
    0.55
    ħĭ
    0.55
    ators
    0.55
    sonian
    0.53
    ational
    0.53
    UCT
    0.52
    rosso
    0.51
     exha
    0.51
    76561
    0.50
    ¥µ
    0.50
    Activations Density 0.068%

    No Known Activations