INDEX

Explanations

phrases related to past actions or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Perſ

-0.65

 raiſ

-0.65

 chofe

-0.63

 الدولى

-0.63

principalTable

-0.63

 againſt

-0.62

Eſ

-0.62

setLayoutManager

-0.61

raisemb

-0.61

новниш

-0.60

POSITIVE LOGITS

做过

0.71

 pernah

0.71

有过

0.66

過的

0.65

เคย

0.64

 past

0.61

见过

0.60

経験

0.59

 precedent

0.58

 been

0.58

Activations Density 0.732%

phrases related to past actions or experiences

No Comments

No Known Activations