INDEX

Explanations

expressions of agreement and support in discussions

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

 архивлан

-0.70

AndroidJUnit

-0.69

writeFieldEnd

-0.67

InputBorder

-0.65

dafx

-0.63

RectangleBorder

-0.63

ReusableCell

-0.63

хьтан

-0.62

noinspection

-0.60

ViewFeatures

-0.60

POSITIVE LOGITS

 mentioned

0.96

 suggestion

0.88

OP

0.86

 above

0.84

mentioned

0.83

 posted

0.82

 comments

0.81

 mention

0.79

 posting

0.78

 commenter

0.77

Activations Density 0.433%

expressions of agreement and support in discussions

No Comments

No Known Activations