INDEX

Explanations

phrases related to compatibility or suitability

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

 שוליים

-0.91

 الحره

-0.86

انجليز

-0.78

Efq

-0.78

 تضيفلها

-0.77

 nahilalakip

-0.77

 Shaksp

-0.75

клопе

-0.75

Autoritní

-0.75

 <<<<<<<<<<<<<<

-0.74

POSITIVE LOGITS

Fits

0.93

 Fits

0.92

 fits

0.90

 snug

0.84

fits

0.83

fit

0.82

fit

0.82

 fitting

0.81

fitting

0.79

FIT

0.75

Activations Density 0.071%

phrases related to compatibility or suitability

No Comments

No Known Activations