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. 9885
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Est" and variations indicating a specific focus or title

    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
    412
    +0.13
    0.5%
    744
    +0.11
    0.4%
    129
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.13
    0.01
    555
    +0.11
    0.01
    744
    +0.11
    0.02
    Negative Logits
    bur
    -0.86
    strap
    -0.84
    SpaceEngineers
    -0.80
    BALL
    -0.80
    FACE
    -0.80
    spr
    -0.79
    beit
    -0.78
    die
    -0.74
     Crusade
    -0.73
    trap
    -0.73
    POSITIVE LOGITS
    ablished
    1.27
    imate
    1.24
    ablish
    1.22
    imates
    1.19
    asonic
    1.00
    uary
    1.00
     Est
    0.96
    imating
    0.92
    imize
    0.90
    Est
    0.87
    Activations Density 0.011%

    No Known Activations