© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45775
    Prev
    Next
    INDEX
    Explanations

    references to city development and urban planning, particularly focusing on downtown areas

    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
    +0.23
    1.0%
    288
    +0.16
    0.7%
    488
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.20
    649
    +0.16
    0.04
    522
    +0.12
    0.08
    Negative Logits
    ktop
    -0.96
    gger
    -0.93
    nir
    -0.90
    uth
    -0.85
    BuyableInstoreAndOnline
    -0.84
    uid
    -0.81
     Canaver
    -0.80
    ula
    -0.78
    catentry
    -0.76
    udic
    -0.74
    POSITIVE LOGITS
     skyline
    0.99
     redevelopment
    0.96
     skysc
    0.94
     plaza
    0.88
     downtown
    0.82
     park
    0.81
     district
    0.81
     mall
    0.80
     street
    0.79
     waterfront
    0.79
    Activations Density 8.147%

    No Known Activations