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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1370
    Prev
    Next
    INDEX
    Explanations

    references to the concept of neutrality or neutralizing 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
    288
    +0.21
    1.0%
    153
    +0.11
    0.5%
    642
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.09
    151
    +0.11
    0.06
    329
    +0.10
    0.04
    Negative Logits
     millenn
    -0.83
    soDeliveryDate
    -0.81
    MAT
    -0.81
    Hop
    -0.80
    INFO
    -0.79
    HAEL
    -0.79
    ECH
    -0.79
    ograp
    -0.76
    KER
    -0.76
    Mill
    -0.75
    POSITIVE LOGITS
    izing
    0.94
    ization
    0.89
    ity
    0.87
    izes
    0.85
    izers
    0.82
     buoy
    0.80
    ities
    0.80
    estine
    0.80
    ize
    0.79
     neutrality
    0.79
    Activations Density 1.168%

    No Known Activations