© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 3620
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing the importance, nature, idea, ultimate goal, or reflection of something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.33
    1.3%
    608
    +0.13
    0.5%
    479
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.33
    0.09
    393
    +0.13
    0.10
    608
    +0.13
    0.09
    Negative Logits
    apons
    -0.87
    gdala
    -0.85
    rn
    -0.83
    staking
    -0.82
    cles
    -0.82
    rade
    -0.82
    berry
    -0.82
    each
    -0.81
    itaire
    -0.79
    alcohol
    -0.78
    POSITIVE LOGITS
     consolation
    1.11
     biggest
    1.08
     temptation
    1.04
     simplest
    1.04
     same
    1.03
     easiest
    1.02
     hallmark
    1.01
     greatest
    1.01
    ocratic
    1.00
     motivation
    1.00
    Activations Density 1.088%

    No Known Activations