INDEX

Explanations

phrases that involve judgment or evaluation of people, ideas, or situations

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

出版年

-0.66

 iprot

-0.64

 springfox

-0.61

quartered

-0.61

igshid

-0.60

scriptcase

-0.59

ंदीखरीदारी

-0.59

ftagPool

-0.59

 bezeichneter

-0.58

 ModelExpression

-0.57

POSITIVE LOGITS

 étant

0.76

 worthy

0.76

0.69

“

0.69

 worthwhile

0.64

posedge

0.63

0.62

‘

0.62

 having

0.62

 suitable

0.61

Activations Density 0.524%

phrases that involve judgment or evaluation of people, ideas, or situations

No Comments

No Known Activations