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. 5389
    Prev
    Next
    INDEX
    Explanations

    references to non-governmental organizations (NGOs)

    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
    248
    +0.09
    0.5%
    231
    +0.09
    0.5%
    127
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.03
    326
    +0.09
    0.02
    656
    +0.08
    0.02
    Negative Logits
     Sul
    -0.68
    hyde
    -0.59
    fired
    -0.58
    icio
    -0.56
     Reincarn
    -0.53
    aceous
    -0.53
    role
    -0.52
    ranged
    -0.52
    hips
    -0.51
    itation
    -0.50
    POSITIVE LOGITS
     nomine
    0.67
    icut
    0.65
    ħĭ
    0.64
    rg
    0.59
    Ops
    0.59
    CCC
    0.58
    opt
    0.58
    asus
    0.57
     mosqu
    0.57
    nik
    0.57
    Activations Density 0.077%

    No Known Activations