INDEX

Explanations

calls to action for users to try or experiment with something

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

">+

-0.55

]=$

-0.52

}{*}{}

-0.52

∙

-0.50

 perfectly

-0.49

">—

-0.48

󠁣

-0.48

">.

-0.47

perfectly

-0.47

 Mase

-0.47

POSITIVE LOGITS

 kræ

0.84

 MainAxisSize

0.74

out

0.72

Different

0.71

 Different

0.69

different

0.67

 GenerationType

0.67

évaluateur

0.67

 different

0.66

 Roskov

0.65

Activations Density 0.086%

calls to action for users to try or experiment with something

No Comments

No Known Activations