© 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 Local
    5. 6-RES_SCL-AJT
    6. 39935
    Prev
    Next
    INDEX
    Explanations

    phrases related to trust and confidence in institutions and technologies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    +0.15
    0.7%
    283
    +0.12
    0.5%
    607
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.15
    0.26
    283
    +0.12
    0.01
    608
    +0.11
    0.15
    Negative Logits
    ãĥķãĤ©
    -0.82
    netflix
    -0.81
    imilar
    -0.77
    ycle
    -0.74
    pain
    -0.74
    utan
    -0.73
    selage
    -0.73
    traumatic
    -0.72
    ener
    -0.71
    jee
    -0.71
    POSITIVE LOGITS
    worthiness
    1.03
     sincerity
    0.95
     assurance
    0.93
     judgment
    0.89
     integrity
    0.88
     trusting
    0.86
     judgement
    0.86
     reliability
    0.84
     credibility
    0.81
     legitimacy
    0.80
    Activations Density 10.278%

    No Known Activations