© 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. 46020
    Prev
    Next
    INDEX
    Explanations

    code syntax patterns and commands in a programming context

    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
    551
    +0.06
    0.5%
    484
    +0.05
    0.5%
    301
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.06
    0.23
    373
    +0.05
    -0.20
    442
    +0.05
    0.08
    Negative Logits
    fulness
    -0.40
    walker
    -0.38
     Lauder
    -0.35
    urned
    -0.35
    gger
    -0.34
    onom
    -0.33
    bledon
    -0.32
    blers
    -0.32
    åĤ
    -0.32
     skelet
    -0.31
    POSITIVE LOGITS
    @#
    0.44
     @@
    0.44
    interstitial
    0.42
    inventoryQuantity
    0.41
    names
    0.40
    @@
    0.39
    SOURCE
    0.38
    USE
    0.38
    odder
    0.36
    UTERS
    0.35
    Activations Density 10.241%

    No Known Activations