© 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. 35086
    Prev
    Next
    INDEX
    Explanations

    medical terms related to the male reproductive system

    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
    526
    +0.17
    0.7%
    421
    +0.16
    0.6%
    99
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.17
    0.10
    51
    +0.16
    0.09
    240
    +0.15
    0.07
    Negative Logits
    TAIN
    -1.06
    ÄŁ
    -0.94
    cles
    -0.91
    ÃįÃį
    -0.85
    hyde
    -0.81
    ITAL
    -0.80
    cules
    -0.77
    FINEST
    -0.75
    CLASSIFIED
    -0.74
    ELY
    -0.73
    POSITIVE LOGITS
    itz
    1.31
    itched
    1.21
    adiator
    1.15
    itter
    1.12
    acial
    1.12
    ancing
    1.10
    immer
    1.10
    amping
    1.09
    anz
    1.09
    ashing
    1.07
    Activations Density 6.312%

    No Known Activations