© 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. 12735
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and government affairs

    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
    +0.11
    0.6%
    119
    +0.08
    0.5%
    753
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.27
    375
    +0.08
    0.08
    393
    +0.08
    0.26
    Negative Logits
     Sands
    -0.62
    osa
    -0.62
    afety
    -0.58
     Peaks
    -0.57
     Canterbury
    -0.55
     Mitchell
    -0.54
    Rus
    -0.53
    istries
    -0.53
     Burgess
    -0.53
    alez
    -0.53
    POSITIVE LOGITS
     mileage
    0.63
    etheless
    0.63
     cosmetic
    0.59
     satisfying
    0.57
     identical
    0.56
     indistinguishable
    0.55
     unint
    0.54
     intact
    0.52
     likely
    0.52
     pointless
    0.52
    Activations Density 10.334%

    No Known Activations