INDEX

Explanations

vague or ambiguous language that lacks specificity

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

います

-0.49

 pois

-0.49

both

-0.48

ifstream

-0.47

 both

-0.46

||

-0.44

&&

-0.43

みましょう

-0.42

par

-0.42

 determin

-0.41

POSITIVE LOGITS

 utafitiHapana

0.92

########.

0.91

 insuffisamment

0.85

 doInBackground

0.84

openzeppelin

0.80

CppMethod

0.75

ftagPool

0.73

 stuff

0.69

subpackage

0.67

 متعلقه

0.67

Activations Density 0.126%

vague or ambiguous language that lacks specificity

No Comments

No Known Activations