© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 40746
    Prev
    Next
    INDEX
    Explanations

    phrases related to listening and conversation

    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
    523
    +0.07
    0.5%
    496
    +0.07
    0.5%
    271
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    273
    +0.07
    0.10
    241
    +0.07
    0.08
    659
    +0.06
    0.08
    Negative Logits
    acea
    -0.44
     glide
    -0.42
     Sabha
    -0.42
    ktop
    -0.41
     unnecess
    -0.40
     caste
    -0.38
     Scotia
    -0.37
    chy
    -0.37
    abad
    -0.37
     gre
    -0.36
    POSITIVE LOGITS
    ership
    0.82
    Listen
    0.59
    ings
    0.56
    ers
    0.55
     Listen
    0.53
    ances
    0.52
    eport
    0.51
    oyle
    0.48
     listen
    0.48
    INGS
    0.48
    Activations Density 5.739%

    No Known Activations