© 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. 13960
    Prev
    Next
    INDEX
    Explanations

    written materials such as pamphlets, brochures, flyers, and leaflets

    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
    679
    +0.09
    0.6%
    447
    +0.09
    0.6%
    344
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.21
    235
    +0.09
    0.12
    289
    +0.07
    -0.01
    Negative Logits
     saline
    -0.46
    arella
    -0.45
    pine
    -0.43
     Rover
    -0.43
     negligence
    -0.42
    agara
    -0.41
     enrichment
    -0.41
     Mysteries
    -0.40
     Odyssey
    -0.40
    engeance
    -0.40
    POSITIVE LOGITS
     pamph
    0.68
     leaflets
    0.63
    lets
    0.59
     flyer
    0.59
     pamphlet
    0.58
    isode
    0.57
    lete
    0.57
     Niet
    0.57
    pared
    0.57
    let
    0.55
    Activations Density 7.034%

    No Known Activations