© 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. 14089
    Prev
    Next
    INDEX
    Explanations

    names of locations or brands related to products

    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
    401
    +0.12
    0.5%
    447
    +0.11
    0.5%
    39
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.12
    0.14
    39
    +0.11
    0.12
    134
    +0.11
    0.08
    Negative Logits
    eve
    -0.67
     reconcil
    -0.65
     metic
    -0.61
    rency
    -0.60
     relent
    -0.59
     unaff
    -0.57
     scope
    -0.57
     potency
    -0.57
     NEC
    -0.57
     notice
    -0.57
    POSITIVE LOGITS
    angelo
    0.93
    sels
    0.92
    asus
    0.80
    baum
    0.80
    achus
    0.79
    γ
    0.76
    zee
    0.75
    bon
    0.75
    hler
    0.71
    ãĤ£
    0.71
    Activations Density 17.232%

    No Known Activations