INDEX

Explanations

references to large quantities or sizes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 invokingState

-0.69

 judiciales

-0.68

новен

-0.66

жидан

-0.66

 régal

-0.65

 Hobson

-0.65

 dépos

-0.64

 cumpli

-0.64

تيجة

-0.63

 obligé

-0.63

POSITIVE LOGITS

Large

1.80

 large

1.79

 Large

1.78

 LARGE

1.72

LARGE

1.72

large

1.67

 larges

1.38

 larger

1.33

 Larger

1.31

Larger

1.28

Activations Density 0.105%

references to large quantities or sizes

No Comments

No Known Activations