INDEX

Explanations

phrases related to achieving positive outcomes or results

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ukunft

-0.67

TestBed

-0.59

RectangleBorder

-0.59

omenclature

-0.59

jgl

-0.58

|}{\

-0.55

csolódó

-0.55

 chargés

-0.54

 nakalista

-0.54

PropertyChanging

-0.54

POSITIVE LOGITS

 achieved

2.47

achieved

2.07

 attained

2.01

 achieve

1.94

Achie

1.90

 Achie

1.80

 achieves

1.77

 achieving

1.75

achieve

1.72

 achievement

1.69

Activations Density 0.887%

phrases related to achieving positive outcomes or results

No Comments

No Known Activations