INDEX

Explanations

comparative terms indicating levels of measurement or concentration

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

+#+#

-1.04

новниш

-0.79

Cult

-0.73

 Cult

-0.68

enumi

-0.65

цепт

-0.60

 SwitchCompat

-0.59

forgotten

-0.57

Obsolete

-0.56

flüs

-0.56

POSITIVE LOGITS

 Lower

1.01

Lower

0.96

Higher

0.90

 Higher

0.90

 lower

0.86

 Upper

0.83

LOWER

0.83

 higher

0.83

Upper

0.80

 LOWER

0.79

Activations Density 0.233%

comparative terms indicating levels of measurement or concentration

No Comments

No Known Activations