© 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. 3815
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific locations, particularly Adelaide, and names of people or places within or associated with Adelaide

    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
    447
    +0.08
    0.7%
    99
    +0.08
    0.6%
    71
    +0.07
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.20
    699
    +0.08
    0.03
    99
    +0.07
    0.09
    Negative Logits
    \\\\\\\\
    -0.48
    ning
    -0.47
    loo
    -0.46
    colo
    -0.46
    liness
    -0.44
    \\\\\\\\\\\\\\\\
    -0.43
    fare
    -0.42
    eled
    -0.42
    hof
    -0.41
    kefeller
    -0.40
    POSITIVE LOGITS
    inates
    0.50
    auri
    0.47
    icago
    0.46
    inite
    0.46
    inately
    0.46
    inant
    0.44
    iour
    0.43
    inations
    0.42
    incinn
    0.42
    ansson
    0.42
    Activations Density 8.363%

    No Known Activations