© 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. 39907
    Prev
    Next
    INDEX
    Explanations

    places, people or objects being taken or transported somewhere

    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
    +0.19
    0.9%
    566
    +0.13
    0.6%
    240
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    222
    +0.19
    0.07
    393
    +0.13
    0.20
    475
    +0.12
    0.08
    Negative Logits
    ulo
    -0.74
    lich
    -0.72
     insurg
    -0.65
    cape
    -0.64
    eers
    -0.62
     sclerosis
    -0.59
    gian
    -0.59
    robe
    -0.59
     nomine
    -0.57
    earances
    -0.57
    POSITIVE LOGITS
     aback
    1.34
    aways
    1.06
     care
    0.86
     advantage
    0.85
     cogn
    0.85
    OVER
    0.82
    ardless
    0.81
     INTO
    0.78
     away
    0.77
     heed
    0.75
    Activations Density 8.742%

    No Known Activations