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 @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

actéristique

-0.63

drawSprites

-0.60

olesale

-0.59

InputBorder

-0.58

"?>

-0.58

 fhort

-0.57

 fhew

-0.56

dafx

-0.55

ndose

-0.55

 motherfucker

-0.55

POSITIVE LOGITS

0.78

OP

0.73

 regarding

0.71

 above

0.69

 earlier

0.69

Regarding

0.63

 ovan

0.62

 выше

0.62

earlier

0.61

regarding

0.61

Activations Density 0.274%

expressions of agreement and support in discussions

No Comments

No Known Activations