INDEX

Explanations

phrases related to tasks and their completion

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

matchCondition

-0.53

鰭

-0.52

ScreenState

-0.51

 géographie

-0.50

tainen

-0.49

 Availability

-0.48

 Immediate

-0.47

Carreira

-0.47

<bos>

-0.46

Amm

-0.46

POSITIVE LOGITS

 efficiently

0.94

 PROPER

0.88

 properly

0.86

 correctly

0.86

 flawlessly

0.84

efficient

0.82

Proper

0.81

 proprement

0.79

 proper

0.78

 smarter

0.78

Activations Density 0.212%

phrases related to tasks and their completion

No Comments

No Known Activations