© 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. 3780
    Prev
    Next
    INDEX
    Explanations

    references to the specific term "Rem" followed by a single digit, potentially related to different versions or aspects of a concept or entity named "Rem"

    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
    503
    +0.21
    0.9%
    447
    +0.15
    0.6%
    232
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.21
    0.05
    503
    +0.15
    0.04
    677
    +0.14
    0.07
    Negative Logits
    glers
    -0.90
    gerald
    -0.83
    tips
    -0.78
     McCabe
    -0.73
    SHIP
    -0.71
    bags
    -0.68
     Labrador
    -0.68
    WAY
    -0.65
    walk
    -0.65
    OHN
    -0.65
    POSITIVE LOGITS
    nants
    1.41
    arkable
    1.37
    ovable
    1.31
    ittance
    1.31
    edy
    1.31
    oving
    1.27
    nant
    1.20
    ark
    1.18
    arks
    1.18
    aining
    1.16
    Activations Density 6.152%

    No Known Activations