INDEX

Explanations

terms and phrases related to completeness or entirety

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+

-0.77

 altogether

-0.65

 vivement

-0.57

 célèbres

-0.54

EDEFAULT

-0.53

 wholly

-0.53

 Wicidata

-0.51

 soucis

-0.51

 slightest

-0.51

 ícones

-0.51

POSITIVE LOGITS

 blown

1.01

 fled

0.97

blown

0.90

fledged

0.90

 disclosure

0.78

 throttle

0.74

 spectrum

0.73

erton

0.73

fillment

0.72

 moon

0.72

Activations Density 0.136%

terms and phrases related to completeness or entirety

No Comments

No Known Activations