Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13194
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotions and actions

    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%
    690
    +0.09
    0.4%
    758
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.15
    0.11
    665
    +0.09
    0.18
    123
    +0.09
    0.12
    Negative Logits
    bow
    -0.65
    ption
    -0.58
    cele
    -0.56
    mage
    -0.56
    ilings
    -0.55
    toggle
    -0.55
    majority
    -0.53
     Ce
    -0.53
    Introduced
    -0.53
    guide
    -0.53
    POSITIVE LOGITS
     raining
    0.81
     tremend
    0.70
    bnb
    0.66
     easier
    0.65
     alot
    0.63
     doub
    0.60
     downhill
    0.60
     awfully
    0.59
    chwitz
    0.59
     CTR
    0.58
    Activations Density 9.409%

    No Known Activations