© 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
    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. 33972
    Prev
    Next
    INDEX
    Explanations

    sentences related to parenting advice and personal anecdotes

    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
    737
    +0.07
    0.5%
    626
    +0.06
    0.5%
    225
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.07
    0.31
    14
    +0.06
    0.09
    267
    +0.06
    0.11
    Negative Logits
    enhagen
    -0.44
     Nile
    -0.43
    VIDEO
    -0.41
     pige
    -0.39
    neys
    -0.38
     Pigs
    -0.37
     seats
    -0.37
    DAQ
    -0.36
    Accessory
    -0.35
     precincts
    -0.35
    POSITIVE LOGITS
    rencies
    0.50
    irin
    0.45
    hing
    0.44
    olate
    0.42
    ty
    0.41
    ional
    0.40
    inational
    0.40
    reck
    0.40
    etsk
    0.39
    olt
    0.39
    Activations Density 12.711%

    No Known Activations