INDEX

Explanations

beginning or opening markers in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

IsContent

-0.89

 iſt

-0.83

 myſelf

-0.80

 ſhe

-0.78

 raiſ

-0.78

 uſed

-0.77

 itſelf

-0.75

 ſte

-0.74

 preſ

-0.73

uſ

-0.73

POSITIVE LOGITS

Enllaces

0.61

BeginContext

0.57

<eos>

0.53

 censo

0.52

shtml

0.52

了吧

0.51

/*

0.51

 zboží

0.49

brado

0.47

Activations Density 0.056%

beginning or opening markers in a text

No Comments

No Known Activations