© 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. 14553
    Prev
    Next
    INDEX
    Explanations

    topics or instances related to fear or causing fear

    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
    326
    +0.18
    0.7%
    578
    +0.14
    0.6%
    119
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.13
    288
    +0.14
    0.15
    730
    +0.13
    0.08
    Negative Logits
    edded
    -0.94
    ault
    -0.91
    iciency
    -0.91
    ional
    -0.91
    ugal
    -0.89
    actions
    -0.88
    arian
    -0.86
    iance
    -0.85
    iations
    -0.85
    iances
    -0.85
    POSITIVE LOGITS
    crow
    1.97
    mong
    1.27
    vana
    0.92
     Haram
    0.88
    abies
    0.84
    tty
    0.82
    warts
    0.80
    faced
    0.80
     Ducks
    0.78
     Panda
    0.78
    Activations Density 2.519%

    No Known Activations