© 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
    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. 45855
    Prev
    Next
    INDEX
    Explanations

    names of people and locations, especially related to historical events

    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
    240
    +0.03
    0.5%
    368
    +0.03
    0.5%
    391
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    179
    +0.03
    0.09
    767
    +0.03
    0.09
    284
    +0.03
    0.10
    Negative Logits
     somet
    -0.22
     Swordsman
    -0.21
    pole
    -0.21
    ulhu
    -0.20
     isEnabled
    -0.20
    inosaur
    -0.20
     scales
    -0.20
     epile
    -0.19
    ensor
    -0.19
    ritic
    -0.19
    POSITIVE LOGITS
    lain
    0.23
    hua
    0.23
    gar
    0.22
    ira
    0.22
    aii
    0.22
    lla
    0.22
    edu
    0.22
     Blanc
    0.21
    gars
    0.21
    ously
    0.21
    Activations Density 14.666%

    No Known Activations