© 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. 6062
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing strong opinions or beliefs

    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
    447
    +0.29
    1.1%
    673
    +0.14
    0.5%
    213
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.29
    0.04
    266
    +0.14
    0.17
    85
    +0.12
    0.12
    Negative Logits
    oulos
    -1.06
    imbabwe
    -0.98
    inkle
    -0.93
    aghd
    -0.90
    akespe
    -0.79
    ribly
    -0.79
    umbledore
    -0.79
    intage
    -0.78
    ouri
    -0.78
    NOW
    -0.77
    POSITIVE LOGITS
     Flavoring
    0.94
     accelerate
    0.76
     Aerospace
    0.72
     accelerated
    0.72
     accur
    0.71
     Jiu
    0.70
    abilia
    0.70
     Mant
    0.70
     Devils
    0.69
     Reincarn
    0.69
    Activations Density 3.422%

    No Known Activations